Upload folder using huggingface_hub

README.md

@@ -0,0 +1,60 @@
+---
+library_name: transformers
+license: other
+base_model: deepseek-ai/deepseek-coder-7b-instruct-v1.5
+tags:
+- llama-factory
+- freeze
+- generated_from_trainer
+model-index:
+- name: deepseep_nsx
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# deepseep_nsx
+
+This model is a fine-tuned version of [deepseek-ai/deepseek-coder-7b-instruct-v1.5](https://huggingface.co/deepseek-ai/deepseek-coder-7b-instruct-v1.5) on the codes_330k_nsx dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 16
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 512
+- total_eval_batch_size: 32
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- num_epochs: 1.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.48.2
+- Pytorch 2.5.1+cu124
+- Datasets 3.2.0
+- Tokenizers 0.21.0

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9991836734693877,
+    "num_input_tokens_seen": 320864256,
+    "total_flos": 1.2496254746971079e+19,
+    "train_loss": 0.5089508540490094,
+    "train_runtime": 7110.2315,
+    "train_samples_per_second": 11.018,
+    "train_steps_per_second": 0.022
+}

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "deepseek-ai/deepseek-coder-7b-instruct-v1.5",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 100000,
+  "eos_token_id": 100015,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 30,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "factor": 1.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 4096,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.2",
+  "use_cache": false,
+  "vocab_size": 102400
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 100000,
+  "eos_token_id": 100015,
+  "transformers_version": "4.48.2"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28aba7f82f5ce656674a3e922d68c0b7bd12d2f2e6da09e47fa72eec539c53c2
+size 4987202208

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9e815d13d98a67f7370ade76666bfa350f8083dea55f75a60050d05d8bb0728
+size 4980945440

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4852887bf380547ed6fcbac3c677d51f7a3e906f18a93d27f7b858a79727f9e1
+size 4662148920

model.safetensors.index.json

@@ -0,0 +1,280 @@
+{
+  "metadata": {
+    "total_size": 14630264832
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00003-of-00003.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|EOT|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,149 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "100000": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100001": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100002": {
+      "content": "ø",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100003": {
+      "content": "ö",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100004": {
+      "content": "ú",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100005": {
+      "content": "ÿ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100006": {
+      "content": "õ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100007": {
+      "content": "÷",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100008": {
+      "content": "û",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100009": {
+      "content": "ý",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100010": {
+      "content": "À",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100011": {
+      "content": "ù",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100012": {
+      "content": "Á",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100013": {
+      "content": "þ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100014": {
+      "content": "ü",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100015": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{% if not add_generation_prompt is defined %}\n{% set add_generation_prompt = false %}\n{% endif %}\n{%- set ns = namespace(found=false) -%}\n{%- for message in messages -%}\n    {%- if message['role'] == 'system' -%}\n        {%- set ns.found = true -%}\n    {%- endif -%}\n{%- endfor -%}\n{{bos_token}}{%- if not ns.found -%}\n{{'You are an AI programming assistant, utilizing the Deepseek Coder model, developed by Deepseek Company, and you only answer questions related to computer science. For politically sensitive questions, security and privacy issues, and other non-computer science questions, you will refuse to answer\\n'}}\n{%- endif %}\n{%- for message in messages %}\n    {%- if message['role'] == 'system' %}\n{{ message['content'] }}\n    {%- else %}\n        {%- if message['role'] == 'user' %}\n{{'### Instruction:\\n' + message['content'] + '\\n'}}\n        {%- else %}\n{{'### Response:\\n' + message['content'] + '\\n<|EOT|>\\n'}}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{% if add_generation_prompt %}\n{{'### Response:'}}\n{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|EOT|>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 4096,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9991836734693877,
+    "num_input_tokens_seen": 320864256,
+    "total_flos": 1.2496254746971079e+19,
+    "train_loss": 0.5089508540490094,
+    "train_runtime": 7110.2315,
+    "train_samples_per_second": 11.018,
+    "train_steps_per_second": 0.022
+}

trainer_log.jsonl

@@ -0,0 +1,154 @@
+{"current_steps": 1, "total_steps": 153, "loss": 0.7016, "lr": 4.999472998758978e-05, "epoch": 0.006530612244897959, "percentage": 0.65, "elapsed_time": "0:00:48", "remaining_time": "2:03:00", "throughput": 43192.86, "total_tokens": 2097152}
+{"current_steps": 2, "total_steps": 153, "loss": 0.6549, "lr": 4.99789221722016e-05, "epoch": 0.013061224489795919, "percentage": 1.31, "elapsed_time": "0:01:34", "remaining_time": "1:58:33", "throughput": 44515.99, "total_tokens": 4194304}
+{"current_steps": 3, "total_steps": 153, "loss": 0.6414, "lr": 4.995258321842611e-05, "epoch": 0.019591836734693877, "percentage": 1.96, "elapsed_time": "0:02:20", "remaining_time": "1:56:45", "throughput": 44905.05, "total_tokens": 6291456}
+{"current_steps": 4, "total_steps": 153, "loss": 0.6061, "lr": 4.991572423079236e-05, "epoch": 0.026122448979591838, "percentage": 2.61, "elapsed_time": "0:03:06", "remaining_time": "1:55:34", "throughput": 45061.25, "total_tokens": 8388608}
+{"current_steps": 5, "total_steps": 153, "loss": 0.6026, "lr": 4.986836074908616e-05, "epoch": 0.0326530612244898, "percentage": 3.27, "elapsed_time": "0:03:52", "remaining_time": "1:54:43", "throughput": 45092.72, "total_tokens": 10485760}
+{"current_steps": 6, "total_steps": 153, "loss": 0.5596, "lr": 4.98105127417984e-05, "epoch": 0.03918367346938775, "percentage": 3.92, "elapsed_time": "0:04:38", "remaining_time": "1:53:50", "throughput": 45134.9, "total_tokens": 12582912}
+{"current_steps": 7, "total_steps": 153, "loss": 0.557, "lr": 4.974220459770639e-05, "epoch": 0.045714285714285714, "percentage": 4.58, "elapsed_time": "0:05:25", "remaining_time": "1:52:59", "throughput": 45166.2, "total_tokens": 14680064}
+{"current_steps": 8, "total_steps": 153, "loss": 0.5416, "lr": 4.966346511559149e-05, "epoch": 0.052244897959183675, "percentage": 5.23, "elapsed_time": "0:06:11", "remaining_time": "1:52:14", "throughput": 45150.78, "total_tokens": 16777216}
+{"current_steps": 9, "total_steps": 153, "loss": 0.5424, "lr": 4.957432749209755e-05, "epoch": 0.05877551020408163, "percentage": 5.88, "elapsed_time": "0:06:57", "remaining_time": "1:51:25", "throughput": 45171.68, "total_tokens": 18874368}
+{"current_steps": 10, "total_steps": 153, "loss": 0.5242, "lr": 4.9474829307735115e-05, "epoch": 0.0653061224489796, "percentage": 6.54, "elapsed_time": "0:07:44", "remaining_time": "1:50:35", "throughput": 45195.61, "total_tokens": 20971520}
+{"current_steps": 11, "total_steps": 153, "loss": 0.5195, "lr": 4.9365012511037514e-05, "epoch": 0.07183673469387755, "percentage": 7.19, "elapsed_time": "0:08:30", "remaining_time": "1:49:48", "throughput": 45199.34, "total_tokens": 23068672}
+{"current_steps": 12, "total_steps": 153, "loss": 0.5259, "lr": 4.9244923400875245e-05, "epoch": 0.0783673469387755, "percentage": 7.84, "elapsed_time": "0:09:16", "remaining_time": "1:49:02", "throughput": 45198.53, "total_tokens": 25165824}
+{"current_steps": 13, "total_steps": 153, "loss": 0.521, "lr": 4.911461260693638e-05, "epoch": 0.08489795918367347, "percentage": 8.5, "elapsed_time": "0:10:03", "remaining_time": "1:48:14", "throughput": 45206.71, "total_tokens": 27262976}
+{"current_steps": 14, "total_steps": 153, "loss": 0.5269, "lr": 4.8974135068381036e-05, "epoch": 0.09142857142857143, "percentage": 9.15, "elapsed_time": "0:10:49", "remaining_time": "1:47:29", "throughput": 45199.56, "total_tokens": 29360128}
+{"current_steps": 15, "total_steps": 153, "loss": 0.5208, "lr": 4.882355001067892e-05, "epoch": 0.09795918367346938, "percentage": 9.8, "elapsed_time": "0:11:36", "remaining_time": "1:46:45", "throughput": 45179.98, "total_tokens": 31457280}
+{"current_steps": 16, "total_steps": 153, "loss": 0.5193, "lr": 4.8662920920639866e-05, "epoch": 0.10448979591836735, "percentage": 10.46, "elapsed_time": "0:12:22", "remaining_time": "1:45:57", "throughput": 45189.12, "total_tokens": 33554432}
+{"current_steps": 17, "total_steps": 153, "loss": 0.4995, "lr": 4.849231551964771e-05, "epoch": 0.1110204081632653, "percentage": 11.11, "elapsed_time": "0:13:08", "remaining_time": "1:45:09", "throughput": 45206.55, "total_tokens": 35651584}
+{"current_steps": 18, "total_steps": 153, "loss": 0.5277, "lr": 4.8311805735108894e-05, "epoch": 0.11755102040816326, "percentage": 11.76, "elapsed_time": "0:13:54", "remaining_time": "1:44:21", "throughput": 45215.87, "total_tokens": 37748736}
+{"current_steps": 19, "total_steps": 153, "loss": 0.5187, "lr": 4.81214676701278e-05, "epoch": 0.12408163265306123, "percentage": 12.42, "elapsed_time": "0:14:41", "remaining_time": "1:43:35", "throughput": 45208.94, "total_tokens": 39845888}
+{"current_steps": 20, "total_steps": 153, "loss": 0.5322, "lr": 4.792138157142158e-05, "epoch": 0.1306122448979592, "percentage": 13.07, "elapsed_time": "0:15:27", "remaining_time": "1:42:48", "throughput": 45216.88, "total_tokens": 41943040}
+{"current_steps": 21, "total_steps": 153, "loss": 0.4978, "lr": 4.7711631795488096e-05, "epoch": 0.13714285714285715, "percentage": 13.73, "elapsed_time": "0:16:13", "remaining_time": "1:42:01", "throughput": 45219.43, "total_tokens": 44040192}
+{"current_steps": 22, "total_steps": 153, "loss": 0.5253, "lr": 4.749230677304114e-05, "epoch": 0.1436734693877551, "percentage": 14.38, "elapsed_time": "0:17:00", "remaining_time": "1:41:15", "throughput": 45221.85, "total_tokens": 46137344}
+{"current_steps": 23, "total_steps": 153, "loss": 0.5309, "lr": 4.726349897172791e-05, "epoch": 0.15020408163265306, "percentage": 15.03, "elapsed_time": "0:17:46", "remaining_time": "1:40:28", "throughput": 45221.92, "total_tokens": 48234496}
+{"current_steps": 24, "total_steps": 153, "loss": 0.5197, "lr": 4.702530485714461e-05, "epoch": 0.156734693877551, "percentage": 15.69, "elapsed_time": "0:18:32", "remaining_time": "1:39:41", "throughput": 45230.91, "total_tokens": 50331648}
+{"current_steps": 25, "total_steps": 153, "loss": 0.5115, "lr": 4.677782485216644e-05, "epoch": 0.16326530612244897, "percentage": 16.34, "elapsed_time": "0:19:19", "remaining_time": "1:38:54", "throughput": 45232.96, "total_tokens": 52428800}
+{"current_steps": 26, "total_steps": 153, "loss": 0.4952, "lr": 4.6521163294609196e-05, "epoch": 0.16979591836734695, "percentage": 16.99, "elapsed_time": "0:20:05", "remaining_time": "1:38:08", "throughput": 45227.63, "total_tokens": 54525952}
+{"current_steps": 27, "total_steps": 153, "loss": 0.4781, "lr": 4.625542839324036e-05, "epoch": 0.1763265306122449, "percentage": 17.65, "elapsed_time": "0:20:52", "remaining_time": "1:37:22", "throughput": 45223.72, "total_tokens": 56623104}
+{"current_steps": 28, "total_steps": 153, "loss": 0.5067, "lr": 4.598073218215817e-05, "epoch": 0.18285714285714286, "percentage": 18.3, "elapsed_time": "0:21:38", "remaining_time": "1:36:36", "throughput": 45224.59, "total_tokens": 58720256}
+{"current_steps": 29, "total_steps": 153, "loss": 0.514, "lr": 4.5697190473557946e-05, "epoch": 0.1893877551020408, "percentage": 18.95, "elapsed_time": "0:22:24", "remaining_time": "1:35:48", "throughput": 45234.77, "total_tokens": 60817408}
+{"current_steps": 30, "total_steps": 153, "loss": 0.5062, "lr": 4.540492280890555e-05, "epoch": 0.19591836734693877, "percentage": 19.61, "elapsed_time": "0:23:10", "remaining_time": "1:35:01", "throughput": 45245.47, "total_tokens": 62914560}
+{"current_steps": 31, "total_steps": 153, "loss": 0.494, "lr": 4.510405240853854e-05, "epoch": 0.20244897959183675, "percentage": 20.26, "elapsed_time": "0:23:56", "remaining_time": "1:34:13", "throughput": 45254.52, "total_tokens": 65011712}
+{"current_steps": 32, "total_steps": 153, "loss": 0.5056, "lr": 4.4794706119716455e-05, "epoch": 0.2089795918367347, "percentage": 20.92, "elapsed_time": "0:24:43", "remaining_time": "1:33:27", "throughput": 45249.03, "total_tokens": 67108864}
+{"current_steps": 33, "total_steps": 153, "loss": 0.5128, "lr": 4.447701436314176e-05, "epoch": 0.21551020408163266, "percentage": 21.57, "elapsed_time": "0:25:29", "remaining_time": "1:32:41", "throughput": 45251.42, "total_tokens": 69206016}
+{"current_steps": 34, "total_steps": 153, "loss": 0.5024, "lr": 4.415111107797445e-05, "epoch": 0.2220408163265306, "percentage": 22.22, "elapsed_time": "0:26:15", "remaining_time": "1:31:53", "throughput": 45265.98, "total_tokens": 71303168}
+{"current_steps": 35, "total_steps": 153, "loss": 0.4998, "lr": 4.381713366536311e-05, "epoch": 0.22857142857142856, "percentage": 22.88, "elapsed_time": "0:27:01", "remaining_time": "1:31:07", "throughput": 45263.68, "total_tokens": 73400320}
+{"current_steps": 36, "total_steps": 153, "loss": 0.5222, "lr": 4.347522293051648e-05, "epoch": 0.23510204081632652, "percentage": 23.53, "elapsed_time": "0:27:47", "remaining_time": "1:30:20", "throughput": 45263.37, "total_tokens": 75497472}
+{"current_steps": 37, "total_steps": 153, "loss": 0.501, "lr": 4.312552302333982e-05, "epoch": 0.2416326530612245, "percentage": 24.18, "elapsed_time": "0:28:34", "remaining_time": "1:29:33", "throughput": 45268.14, "total_tokens": 77594624}
+{"current_steps": 38, "total_steps": 153, "loss": 0.5035, "lr": 4.276818137766118e-05, "epoch": 0.24816326530612245, "percentage": 24.84, "elapsed_time": "0:29:20", "remaining_time": "1:28:46", "throughput": 45277.19, "total_tokens": 79691776}
+{"current_steps": 39, "total_steps": 153, "loss": 0.5115, "lr": 4.2403348649073174e-05, "epoch": 0.2546938775510204, "percentage": 25.49, "elapsed_time": "0:30:06", "remaining_time": "1:28:00", "throughput": 45274.06, "total_tokens": 81788928}
+{"current_steps": 40, "total_steps": 153, "loss": 0.5087, "lr": 4.203117865141635e-05, "epoch": 0.2612244897959184, "percentage": 26.14, "elapsed_time": "0:30:52", "remaining_time": "1:27:14", "throughput": 45276.32, "total_tokens": 83886080}
+{"current_steps": 41, "total_steps": 153, "loss": 0.5095, "lr": 4.1651828291931264e-05, "epoch": 0.2677551020408163, "percentage": 26.8, "elapsed_time": "0:31:39", "remaining_time": "1:26:28", "throughput": 45271.83, "total_tokens": 85983232}
+{"current_steps": 42, "total_steps": 153, "loss": 0.5033, "lr": 4.126545750510605e-05, "epoch": 0.2742857142857143, "percentage": 27.45, "elapsed_time": "0:32:25", "remaining_time": "1:25:41", "throughput": 45271.31, "total_tokens": 88080384}
+{"current_steps": 43, "total_steps": 153, "loss": 0.5245, "lr": 4.0872229185248075e-05, "epoch": 0.2808163265306122, "percentage": 28.1, "elapsed_time": "0:33:11", "remaining_time": "1:24:55", "throughput": 45276.9, "total_tokens": 90177536}
+{"current_steps": 44, "total_steps": 153, "loss": 0.5041, "lr": 4.047230911780737e-05, "epoch": 0.2873469387755102, "percentage": 28.76, "elapsed_time": "0:33:58", "remaining_time": "1:24:09", "throughput": 45271.63, "total_tokens": 92274688}
+{"current_steps": 45, "total_steps": 153, "loss": 0.4929, "lr": 4.0065865909481417e-05, "epoch": 0.2938775510204082, "percentage": 29.41, "elapsed_time": "0:34:44", "remaining_time": "1:23:23", "throughput": 45263.66, "total_tokens": 94371840}
+{"current_steps": 46, "total_steps": 153, "loss": 0.4939, "lr": 3.965307091713037e-05, "epoch": 0.3004081632653061, "percentage": 30.07, "elapsed_time": "0:35:31", "remaining_time": "1:22:37", "throughput": 45259.24, "total_tokens": 96468992}
+{"current_steps": 47, "total_steps": 153, "loss": 0.5008, "lr": 3.923409817553284e-05, "epoch": 0.3069387755102041, "percentage": 30.72, "elapsed_time": "0:36:17", "remaining_time": "1:21:51", "throughput": 45263.16, "total_tokens": 98566144}
+{"current_steps": 48, "total_steps": 153, "loss": 0.5023, "lr": 3.880912432401265e-05, "epoch": 0.313469387755102, "percentage": 31.37, "elapsed_time": "0:37:04", "remaining_time": "1:21:05", "throughput": 45260.83, "total_tokens": 100663296}
+{"current_steps": 49, "total_steps": 153, "loss": 0.5124, "lr": 3.837832853196751e-05, "epoch": 0.32, "percentage": 32.03, "elapsed_time": "0:37:50", "remaining_time": "1:20:18", "throughput": 45259.32, "total_tokens": 102760448}
+{"current_steps": 50, "total_steps": 153, "loss": 0.5033, "lr": 3.794189242333106e-05, "epoch": 0.32653061224489793, "percentage": 32.68, "elapsed_time": "0:38:36", "remaining_time": "1:19:32", "throughput": 45265.39, "total_tokens": 104857600}
+{"current_steps": 51, "total_steps": 153, "loss": 0.4958, "lr": 3.7500000000000003e-05, "epoch": 0.3330612244897959, "percentage": 33.33, "elapsed_time": "0:39:22", "remaining_time": "1:18:45", "throughput": 45264.11, "total_tokens": 106954752}
+{"current_steps": 52, "total_steps": 153, "loss": 0.5006, "lr": 3.705283756425872e-05, "epoch": 0.3395918367346939, "percentage": 33.99, "elapsed_time": "0:40:09", "remaining_time": "1:17:59", "throughput": 45261.44, "total_tokens": 109051904}
+{"current_steps": 53, "total_steps": 153, "loss": 0.5033, "lr": 3.6600593640234086e-05, "epoch": 0.3461224489795918, "percentage": 34.64, "elapsed_time": "0:40:55", "remaining_time": "1:17:12", "throughput": 45265.69, "total_tokens": 111149056}
+{"current_steps": 54, "total_steps": 153, "loss": 0.5038, "lr": 3.6143458894413465e-05, "epoch": 0.3526530612244898, "percentage": 35.29, "elapsed_time": "0:41:41", "remaining_time": "1:16:26", "throughput": 45264.02, "total_tokens": 113246208}
+{"current_steps": 55, "total_steps": 153, "loss": 0.4973, "lr": 3.568162605525953e-05, "epoch": 0.35918367346938773, "percentage": 35.95, "elapsed_time": "0:42:28", "remaining_time": "1:15:40", "throughput": 45266.85, "total_tokens": 115343360}
+{"current_steps": 56, "total_steps": 153, "loss": 0.495, "lr": 3.5215289831955786e-05, "epoch": 0.3657142857142857, "percentage": 36.6, "elapsed_time": "0:43:14", "remaining_time": "1:14:53", "throughput": 45270.02, "total_tokens": 117440512}
+{"current_steps": 57, "total_steps": 153, "loss": 0.4971, "lr": 3.474464683231698e-05, "epoch": 0.3722448979591837, "percentage": 37.25, "elapsed_time": "0:44:00", "remaining_time": "1:14:07", "throughput": 45269.97, "total_tokens": 119537664}
+{"current_steps": 58, "total_steps": 153, "loss": 0.5412, "lr": 3.426989547989902e-05, "epoch": 0.3787755102040816, "percentage": 37.91, "elapsed_time": "0:44:46", "remaining_time": "1:13:21", "throughput": 45268.41, "total_tokens": 121634816}
+{"current_steps": 59, "total_steps": 153, "loss": 0.5219, "lr": 3.379123593034342e-05, "epoch": 0.3853061224489796, "percentage": 38.56, "elapsed_time": "0:45:33", "remaining_time": "1:12:34", "throughput": 45272.37, "total_tokens": 123731968}
+{"current_steps": 60, "total_steps": 153, "loss": 0.4989, "lr": 3.330886998699149e-05, "epoch": 0.39183673469387753, "percentage": 39.22, "elapsed_time": "0:46:19", "remaining_time": "1:11:48", "throughput": 45269.65, "total_tokens": 125829120}
+{"current_steps": 61, "total_steps": 153, "loss": 0.5122, "lr": 3.282300101580386e-05, "epoch": 0.3983673469387755, "percentage": 39.87, "elapsed_time": "0:47:05", "remaining_time": "1:11:02", "throughput": 45268.86, "total_tokens": 127926272}
+{"current_steps": 62, "total_steps": 153, "loss": 0.4987, "lr": 3.2333833859621153e-05, "epoch": 0.4048979591836735, "percentage": 40.52, "elapsed_time": "0:47:51", "remaining_time": "1:10:15", "throughput": 45274.18, "total_tokens": 130023424}
+{"current_steps": 63, "total_steps": 153, "loss": 0.4968, "lr": 3.1841574751802076e-05, "epoch": 0.4114285714285714, "percentage": 41.18, "elapsed_time": "0:48:38", "remaining_time": "1:09:29", "throughput": 45270.81, "total_tokens": 132120576}
+{"current_steps": 64, "total_steps": 153, "loss": 0.499, "lr": 3.13464312292752e-05, "epoch": 0.4179591836734694, "percentage": 41.83, "elapsed_time": "0:49:24", "remaining_time": "1:08:42", "throughput": 45270.07, "total_tokens": 134217728}
+{"current_steps": 65, "total_steps": 153, "loss": 0.5055, "lr": 3.084861204504122e-05, "epoch": 0.42448979591836733, "percentage": 42.48, "elapsed_time": "0:50:10", "remaining_time": "1:07:56", "throughput": 45275.01, "total_tokens": 136314880}
+{"current_steps": 66, "total_steps": 153, "loss": 0.5014, "lr": 3.0348327080162435e-05, "epoch": 0.4310204081632653, "percentage": 43.14, "elapsed_time": "0:50:57", "remaining_time": "1:07:10", "throughput": 45267.71, "total_tokens": 138412032}
+{"current_steps": 67, "total_steps": 153, "loss": 0.4892, "lr": 2.9845787255276753e-05, "epoch": 0.43755102040816324, "percentage": 43.79, "elapsed_time": "0:51:44", "remaining_time": "1:06:24", "throughput": 45262.74, "total_tokens": 140509184}
+{"current_steps": 68, "total_steps": 153, "loss": 0.5069, "lr": 2.9341204441673266e-05, "epoch": 0.4440816326530612, "percentage": 44.44, "elapsed_time": "0:52:30", "remaining_time": "1:05:38", "throughput": 45264.29, "total_tokens": 142606336}
+{"current_steps": 69, "total_steps": 153, "loss": 0.4988, "lr": 2.8834791371967142e-05, "epoch": 0.4506122448979592, "percentage": 45.1, "elapsed_time": "0:53:16", "remaining_time": "1:04:51", "throughput": 45263.3, "total_tokens": 144703488}
+{"current_steps": 70, "total_steps": 153, "loss": 0.4771, "lr": 2.8326761550411345e-05, "epoch": 0.45714285714285713, "percentage": 45.75, "elapsed_time": "0:54:02", "remaining_time": "1:04:05", "throughput": 45268.81, "total_tokens": 146800640}
+{"current_steps": 71, "total_steps": 153, "loss": 0.5036, "lr": 2.781732916288303e-05, "epoch": 0.4636734693877551, "percentage": 46.41, "elapsed_time": "0:54:49", "remaining_time": "1:03:18", "throughput": 45271.18, "total_tokens": 148897792}
+{"current_steps": 72, "total_steps": 153, "loss": 0.499, "lr": 2.7306708986582553e-05, "epoch": 0.47020408163265304, "percentage": 47.06, "elapsed_time": "0:55:35", "remaining_time": "1:02:32", "throughput": 45269.61, "total_tokens": 150994944}
+{"current_steps": 73, "total_steps": 153, "loss": 0.5067, "lr": 2.679511629948319e-05, "epoch": 0.476734693877551, "percentage": 47.71, "elapsed_time": "0:56:22", "remaining_time": "1:01:46", "throughput": 45266.0, "total_tokens": 153092096}
+{"current_steps": 74, "total_steps": 153, "loss": 0.5015, "lr": 2.628276678956974e-05, "epoch": 0.483265306122449, "percentage": 48.37, "elapsed_time": "0:57:08", "remaining_time": "1:01:00", "throughput": 45265.72, "total_tokens": 155189248}
+{"current_steps": 75, "total_steps": 153, "loss": 0.504, "lr": 2.5769876463904265e-05, "epoch": 0.4897959183673469, "percentage": 49.02, "elapsed_time": "0:57:54", "remaining_time": "1:00:13", "throughput": 45268.58, "total_tokens": 157286400}
+{"current_steps": 76, "total_steps": 153, "loss": 0.513, "lr": 2.5256661557557247e-05, "epoch": 0.4963265306122449, "percentage": 49.67, "elapsed_time": "0:58:41", "remaining_time": "0:59:27", "throughput": 45264.09, "total_tokens": 159383552}
+{"current_steps": 77, "total_steps": 153, "loss": 0.5093, "lr": 2.4743338442442755e-05, "epoch": 0.5028571428571429, "percentage": 50.33, "elapsed_time": "0:59:27", "remaining_time": "0:58:41", "throughput": 45265.25, "total_tokens": 161480704}
+{"current_steps": 78, "total_steps": 153, "loss": 0.475, "lr": 2.4230123536095748e-05, "epoch": 0.5093877551020408, "percentage": 50.98, "elapsed_time": "1:00:13", "remaining_time": "0:57:54", "throughput": 45263.34, "total_tokens": 163577856}
+{"current_steps": 79, "total_steps": 153, "loss": 0.4827, "lr": 2.3717233210430256e-05, "epoch": 0.5159183673469387, "percentage": 51.63, "elapsed_time": "1:01:00", "remaining_time": "0:57:08", "throughput": 45263.58, "total_tokens": 165675008}
+{"current_steps": 80, "total_steps": 153, "loss": 0.5234, "lr": 2.3204883700516812e-05, "epoch": 0.5224489795918368, "percentage": 52.29, "elapsed_time": "1:01:46", "remaining_time": "0:56:22", "throughput": 45261.98, "total_tokens": 167772160}
+{"current_steps": 81, "total_steps": 153, "loss": 0.5204, "lr": 2.2693291013417453e-05, "epoch": 0.5289795918367347, "percentage": 52.94, "elapsed_time": "1:02:32", "remaining_time": "0:55:35", "throughput": 45265.93, "total_tokens": 169869312}
+{"current_steps": 82, "total_steps": 153, "loss": 0.4886, "lr": 2.2182670837116975e-05, "epoch": 0.5355102040816326, "percentage": 53.59, "elapsed_time": "1:03:19", "remaining_time": "0:54:49", "throughput": 45265.05, "total_tokens": 171966464}
+{"current_steps": 83, "total_steps": 153, "loss": 0.5005, "lr": 2.1673238449588668e-05, "epoch": 0.5420408163265306, "percentage": 54.25, "elapsed_time": "1:04:05", "remaining_time": "0:54:02", "throughput": 45267.62, "total_tokens": 174063616}
+{"current_steps": 84, "total_steps": 153, "loss": 0.4832, "lr": 2.116520862803286e-05, "epoch": 0.5485714285714286, "percentage": 54.9, "elapsed_time": "1:04:51", "remaining_time": "0:53:16", "throughput": 45271.05, "total_tokens": 176160768}
+{"current_steps": 85, "total_steps": 153, "loss": 0.5021, "lr": 2.0658795558326743e-05, "epoch": 0.5551020408163265, "percentage": 55.56, "elapsed_time": "1:05:37", "remaining_time": "0:52:29", "throughput": 45276.0, "total_tokens": 178257920}
+{"current_steps": 86, "total_steps": 153, "loss": 0.4839, "lr": 2.015421274472325e-05, "epoch": 0.5616326530612245, "percentage": 56.21, "elapsed_time": "1:06:23", "remaining_time": "0:51:43", "throughput": 45277.58, "total_tokens": 180355072}
+{"current_steps": 87, "total_steps": 153, "loss": 0.5078, "lr": 1.965167291983757e-05, "epoch": 0.5681632653061225, "percentage": 56.86, "elapsed_time": "1:07:09", "remaining_time": "0:50:57", "throughput": 45276.65, "total_tokens": 182452224}
+{"current_steps": 88, "total_steps": 153, "loss": 0.4981, "lr": 1.9151387954958794e-05, "epoch": 0.5746938775510204, "percentage": 57.52, "elapsed_time": "1:07:55", "remaining_time": "0:50:10", "throughput": 45278.0, "total_tokens": 184549376}
+{"current_steps": 89, "total_steps": 153, "loss": 0.4913, "lr": 1.8653568770724806e-05, "epoch": 0.5812244897959183, "percentage": 58.17, "elapsed_time": "1:08:42", "remaining_time": "0:49:24", "throughput": 45276.64, "total_tokens": 186646528}
+{"current_steps": 90, "total_steps": 153, "loss": 0.4862, "lr": 1.815842524819793e-05, "epoch": 0.5877551020408164, "percentage": 58.82, "elapsed_time": "1:09:28", "remaining_time": "0:48:37", "throughput": 45278.97, "total_tokens": 188743680}
+{"current_steps": 91, "total_steps": 153, "loss": 0.5146, "lr": 1.7666166140378852e-05, "epoch": 0.5942857142857143, "percentage": 59.48, "elapsed_time": "1:10:14", "remaining_time": "0:47:51", "throughput": 45281.93, "total_tokens": 190840832}
+{"current_steps": 92, "total_steps": 153, "loss": 0.4952, "lr": 1.7176998984196146e-05, "epoch": 0.6008163265306122, "percentage": 60.13, "elapsed_time": "1:11:00", "remaining_time": "0:47:05", "throughput": 45282.91, "total_tokens": 192937984}
+{"current_steps": 93, "total_steps": 153, "loss": 0.4845, "lr": 1.6691130013008514e-05, "epoch": 0.6073469387755102, "percentage": 60.78, "elapsed_time": "1:11:47", "remaining_time": "0:46:18", "throughput": 45280.74, "total_tokens": 195035136}
+{"current_steps": 94, "total_steps": 153, "loss": 0.4881, "lr": 1.620876406965658e-05, "epoch": 0.6138775510204082, "percentage": 61.44, "elapsed_time": "1:12:33", "remaining_time": "0:45:32", "throughput": 45281.93, "total_tokens": 197132288}
+{"current_steps": 95, "total_steps": 153, "loss": 0.498, "lr": 1.5730104520100982e-05, "epoch": 0.6204081632653061, "percentage": 62.09, "elapsed_time": "1:13:19", "remaining_time": "0:44:46", "throughput": 45279.92, "total_tokens": 199229440}
+{"current_steps": 96, "total_steps": 153, "loss": 0.4989, "lr": 1.5255353167683017e-05, "epoch": 0.626938775510204, "percentage": 62.75, "elapsed_time": "1:14:06", "remaining_time": "0:43:59", "throughput": 45279.64, "total_tokens": 201326592}
+{"current_steps": 97, "total_steps": 153, "loss": 0.4941, "lr": 1.4784710168044213e-05, "epoch": 0.6334693877551021, "percentage": 63.4, "elapsed_time": "1:14:52", "remaining_time": "0:43:13", "throughput": 45280.37, "total_tokens": 203423744}
+{"current_steps": 98, "total_steps": 153, "loss": 0.4919, "lr": 1.4318373944740484e-05, "epoch": 0.64, "percentage": 64.05, "elapsed_time": "1:15:38", "remaining_time": "0:42:27", "throughput": 45279.2, "total_tokens": 205520896}
+{"current_steps": 99, "total_steps": 153, "loss": 0.5047, "lr": 1.3856541105586545e-05, "epoch": 0.6465306122448979, "percentage": 64.71, "elapsed_time": "1:16:25", "remaining_time": "0:41:40", "throughput": 45280.99, "total_tokens": 207618048}
+{"current_steps": 100, "total_steps": 153, "loss": 0.5104, "lr": 1.339940635976592e-05, "epoch": 0.6530612244897959, "percentage": 65.36, "elapsed_time": "1:17:11", "remaining_time": "0:40:54", "throughput": 45280.87, "total_tokens": 209715200}
+{"current_steps": 101, "total_steps": 153, "loss": 0.5008, "lr": 1.2947162435741278e-05, "epoch": 0.6595918367346939, "percentage": 66.01, "elapsed_time": "1:17:57", "remaining_time": "0:40:08", "throughput": 45281.46, "total_tokens": 211812352}
+{"current_steps": 102, "total_steps": 153, "loss": 0.5022, "lr": 1.2500000000000006e-05, "epoch": 0.6661224489795918, "percentage": 66.67, "elapsed_time": "1:18:43", "remaining_time": "0:39:21", "throughput": 45283.07, "total_tokens": 213909504}
+{"current_steps": 103, "total_steps": 153, "loss": 0.4979, "lr": 1.205810757666894e-05, "epoch": 0.6726530612244898, "percentage": 67.32, "elapsed_time": "1:19:30", "remaining_time": "0:38:35", "throughput": 45280.83, "total_tokens": 216006656}
+{"current_steps": 104, "total_steps": 153, "loss": 0.4972, "lr": 1.1621671468032493e-05, "epoch": 0.6791836734693878, "percentage": 67.97, "elapsed_time": "1:20:16", "remaining_time": "0:37:49", "throughput": 45281.01, "total_tokens": 218103808}
+{"current_steps": 105, "total_steps": 153, "loss": 0.5058, "lr": 1.1190875675987356e-05, "epoch": 0.6857142857142857, "percentage": 68.63, "elapsed_time": "1:21:03", "remaining_time": "0:37:03", "throughput": 45280.08, "total_tokens": 220200960}
+{"current_steps": 106, "total_steps": 153, "loss": 0.4935, "lr": 1.0765901824467167e-05, "epoch": 0.6922448979591836, "percentage": 69.28, "elapsed_time": "1:21:49", "remaining_time": "0:36:16", "throughput": 45277.82, "total_tokens": 222298112}
+{"current_steps": 107, "total_steps": 153, "loss": 0.5041, "lr": 1.0346929082869641e-05, "epoch": 0.6987755102040817, "percentage": 69.93, "elapsed_time": "1:22:36", "remaining_time": "0:35:30", "throughput": 45275.09, "total_tokens": 224395264}
+{"current_steps": 108, "total_steps": 153, "loss": 0.5066, "lr": 9.934134090518593e-06, "epoch": 0.7053061224489796, "percentage": 70.59, "elapsed_time": "1:23:22", "remaining_time": "0:34:44", "throughput": 45275.42, "total_tokens": 226492416}
+{"current_steps": 109, "total_steps": 153, "loss": 0.5181, "lr": 9.527690882192636e-06, "epoch": 0.7118367346938775, "percentage": 71.24, "elapsed_time": "1:24:08", "remaining_time": "0:33:58", "throughput": 45276.2, "total_tokens": 228589568}
+{"current_steps": 110, "total_steps": 153, "loss": 0.4877, "lr": 9.127770814751933e-06, "epoch": 0.7183673469387755, "percentage": 71.9, "elapsed_time": "1:24:55", "remaining_time": "0:33:11", "throughput": 45275.56, "total_tokens": 230686720}
+{"current_steps": 111, "total_steps": 153, "loss": 0.4886, "lr": 8.734542494893955e-06, "epoch": 0.7248979591836735, "percentage": 72.55, "elapsed_time": "1:25:41", "remaining_time": "0:32:25", "throughput": 45275.97, "total_tokens": 232783872}
+{"current_steps": 112, "total_steps": 153, "loss": 0.4986, "lr": 8.348171708068747e-06, "epoch": 0.7314285714285714, "percentage": 73.2, "elapsed_time": "1:26:27", "remaining_time": "0:31:39", "throughput": 45276.87, "total_tokens": 234881024}
+{"current_steps": 113, "total_steps": 153, "loss": 0.4892, "lr": 7.968821348583644e-06, "epoch": 0.7379591836734694, "percentage": 73.86, "elapsed_time": "1:27:13", "remaining_time": "0:30:52", "throughput": 45277.07, "total_tokens": 236978176}
+{"current_steps": 114, "total_steps": 153, "loss": 0.5048, "lr": 7.5966513509268365e-06, "epoch": 0.7444897959183674, "percentage": 74.51, "elapsed_time": "1:28:00", "remaining_time": "0:30:06", "throughput": 45274.06, "total_tokens": 239075328}
+{"current_steps": 115, "total_steps": 153, "loss": 0.4907, "lr": 7.231818622338823e-06, "epoch": 0.7510204081632653, "percentage": 75.16, "elapsed_time": "1:28:46", "remaining_time": "0:29:20", "throughput": 45274.65, "total_tokens": 241172480}
+{"current_steps": 116, "total_steps": 153, "loss": 0.5074, "lr": 6.8744769766601854e-06, "epoch": 0.7575510204081632, "percentage": 75.82, "elapsed_time": "1:29:33", "remaining_time": "0:28:33", "throughput": 45274.14, "total_tokens": 243269632}
+{"current_steps": 117, "total_steps": 153, "loss": 0.4954, "lr": 6.524777069483526e-06, "epoch": 0.7640816326530612, "percentage": 76.47, "elapsed_time": "1:30:19", "remaining_time": "0:27:47", "throughput": 45271.25, "total_tokens": 245366784}
+{"current_steps": 118, "total_steps": 153, "loss": 0.5036, "lr": 6.182866334636889e-06, "epoch": 0.7706122448979592, "percentage": 77.12, "elapsed_time": "1:31:06", "remaining_time": "0:27:01", "throughput": 45270.36, "total_tokens": 247463936}
+{"current_steps": 119, "total_steps": 153, "loss": 0.5133, "lr": 5.848888922025553e-06, "epoch": 0.7771428571428571, "percentage": 77.78, "elapsed_time": "1:31:52", "remaining_time": "0:26:15", "throughput": 45269.11, "total_tokens": 249561088}
+{"current_steps": 120, "total_steps": 153, "loss": 0.4965, "lr": 5.522985636858239e-06, "epoch": 0.7836734693877551, "percentage": 78.43, "elapsed_time": "1:32:38", "remaining_time": "0:25:28", "throughput": 45270.62, "total_tokens": 251658240}
+{"current_steps": 121, "total_steps": 153, "loss": 0.5068, "lr": 5.205293880283552e-06, "epoch": 0.7902040816326531, "percentage": 79.08, "elapsed_time": "1:33:24", "remaining_time": "0:24:42", "throughput": 45273.77, "total_tokens": 253755392}
+{"current_steps": 122, "total_steps": 153, "loss": 0.4993, "lr": 4.8959475914614554e-06, "epoch": 0.796734693877551, "percentage": 79.74, "elapsed_time": "1:34:10", "remaining_time": "0:23:55", "throughput": 45276.01, "total_tokens": 255852544}
+{"current_steps": 123, "total_steps": 153, "loss": 0.5173, "lr": 4.5950771910944605e-06, "epoch": 0.803265306122449, "percentage": 80.39, "elapsed_time": "1:34:57", "remaining_time": "0:23:09", "throughput": 45275.45, "total_tokens": 257949696}
+{"current_steps": 124, "total_steps": 153, "loss": 0.5032, "lr": 4.3028095264420535e-06, "epoch": 0.809795918367347, "percentage": 81.05, "elapsed_time": "1:35:43", "remaining_time": "0:22:23", "throughput": 45275.87, "total_tokens": 260046848}
+{"current_steps": 125, "total_steps": 153, "loss": 0.505, "lr": 4.019267817841835e-06, "epoch": 0.8163265306122449, "percentage": 81.7, "elapsed_time": "1:36:29", "remaining_time": "0:21:36", "throughput": 45276.79, "total_tokens": 262144000}
+{"current_steps": 126, "total_steps": 153, "loss": 0.5145, "lr": 3.7445716067596503e-06, "epoch": 0.8228571428571428, "percentage": 82.35, "elapsed_time": "1:37:16", "remaining_time": "0:20:50", "throughput": 45275.42, "total_tokens": 264241152}
+{"current_steps": 127, "total_steps": 153, "loss": 0.4967, "lr": 3.478836705390809e-06, "epoch": 0.8293877551020408, "percentage": 83.01, "elapsed_time": "1:38:02", "remaining_time": "0:20:04", "throughput": 45276.02, "total_tokens": 266338304}
+{"current_steps": 128, "total_steps": 153, "loss": 0.5001, "lr": 3.222175147833556e-06, "epoch": 0.8359183673469388, "percentage": 83.66, "elapsed_time": "1:38:48", "remaining_time": "0:19:17", "throughput": 45278.83, "total_tokens": 268435456}
+{"current_steps": 129, "total_steps": 153, "loss": 0.5037, "lr": 2.974695142855388e-06, "epoch": 0.8424489795918367, "percentage": 84.31, "elapsed_time": "1:39:34", "remaining_time": "0:18:31", "throughput": 45280.06, "total_tokens": 270532608}
+{"current_steps": 130, "total_steps": 153, "loss": 0.5238, "lr": 2.7365010282720952e-06, "epoch": 0.8489795918367347, "percentage": 84.97, "elapsed_time": "1:40:20", "remaining_time": "0:17:45", "throughput": 45280.01, "total_tokens": 272629760}
+{"current_steps": 131, "total_steps": 153, "loss": 0.5007, "lr": 2.507693226958871e-06, "epoch": 0.8555102040816327, "percentage": 85.62, "elapsed_time": "1:41:07", "remaining_time": "0:16:58", "throughput": 45281.64, "total_tokens": 274726912}
+{"current_steps": 132, "total_steps": 153, "loss": 0.5119, "lr": 2.2883682045119063e-06, "epoch": 0.8620408163265306, "percentage": 86.27, "elapsed_time": "1:41:53", "remaining_time": "0:16:12", "throughput": 45280.63, "total_tokens": 276824064}
+{"current_steps": 133, "total_steps": 153, "loss": 0.4874, "lr": 2.0786184285784297e-06, "epoch": 0.8685714285714285, "percentage": 86.93, "elapsed_time": "1:42:40", "remaining_time": "0:15:26", "throughput": 45277.72, "total_tokens": 278921216}
+{"current_steps": 134, "total_steps": 153, "loss": 0.4969, "lr": 1.8785323298722097e-06, "epoch": 0.8751020408163265, "percentage": 87.58, "elapsed_time": "1:43:26", "remaining_time": "0:14:39", "throughput": 45279.95, "total_tokens": 281018368}
+{"current_steps": 135, "total_steps": 153, "loss": 0.4835, "lr": 1.6881942648911076e-06, "epoch": 0.8816326530612245, "percentage": 88.24, "elapsed_time": "1:44:12", "remaining_time": "0:13:53", "throughput": 45278.63, "total_tokens": 283115520}
+{"current_steps": 136, "total_steps": 153, "loss": 0.4863, "lr": 1.5076844803522922e-06, "epoch": 0.8881632653061224, "percentage": 88.89, "elapsed_time": "1:44:58", "remaining_time": "0:13:07", "throughput": 45280.39, "total_tokens": 285212672}
+{"current_steps": 137, "total_steps": 153, "loss": 0.5046, "lr": 1.3370790793601373e-06, "epoch": 0.8946938775510204, "percentage": 89.54, "elapsed_time": "1:45:45", "remaining_time": "0:12:21", "throughput": 45281.09, "total_tokens": 287309824}
+{"current_steps": 138, "total_steps": 153, "loss": 0.5018, "lr": 1.1764499893210878e-06, "epoch": 0.9012244897959184, "percentage": 90.2, "elapsed_time": "1:46:31", "remaining_time": "0:11:34", "throughput": 45280.82, "total_tokens": 289406976}
+{"current_steps": 139, "total_steps": 153, "loss": 0.5025, "lr": 1.0258649316189722e-06, "epoch": 0.9077551020408163, "percentage": 90.85, "elapsed_time": "1:47:17", "remaining_time": "0:10:48", "throughput": 45281.05, "total_tokens": 291504128}
+{"current_steps": 140, "total_steps": 153, "loss": 0.5139, "lr": 8.85387393063622e-07, "epoch": 0.9142857142857143, "percentage": 91.5, "elapsed_time": "1:48:04", "remaining_time": "0:10:02", "throughput": 45279.91, "total_tokens": 293601280}
+{"current_steps": 141, "total_steps": 153, "loss": 0.484, "lr": 7.550765991247654e-07, "epoch": 0.9208163265306123, "percentage": 92.16, "elapsed_time": "1:48:50", "remaining_time": "0:09:15", "throughput": 45278.68, "total_tokens": 295698432}
+{"current_steps": 142, "total_steps": 153, "loss": 0.5127, "lr": 6.349874889624962e-07, "epoch": 0.9273469387755102, "percentage": 92.81, "elapsed_time": "1:49:37", "remaining_time": "0:08:29", "throughput": 45276.5, "total_tokens": 297795584}
+{"current_steps": 143, "total_steps": 153, "loss": 0.4876, "lr": 5.25170692264887e-07, "epoch": 0.9338775510204081, "percentage": 93.46, "elapsed_time": "1:50:23", "remaining_time": "0:07:43", "throughput": 45275.69, "total_tokens": 299892736}
+{"current_steps": 144, "total_steps": 153, "loss": 0.4925, "lr": 4.256725079024554e-07, "epoch": 0.9404081632653061, "percentage": 94.12, "elapsed_time": "1:51:09", "remaining_time": "0:06:56", "throughput": 45276.41, "total_tokens": 301989888}
+{"current_steps": 145, "total_steps": 153, "loss": 0.4861, "lr": 3.3653488440851255e-07, "epoch": 0.9469387755102041, "percentage": 94.77, "elapsed_time": "1:51:56", "remaining_time": "0:06:10", "throughput": 45274.66, "total_tokens": 304087040}
+{"current_steps": 146, "total_steps": 153, "loss": 0.493, "lr": 2.5779540229361745e-07, "epoch": 0.953469387755102, "percentage": 95.42, "elapsed_time": "1:52:42", "remaining_time": "0:05:24", "throughput": 45273.73, "total_tokens": 306184192}
+{"current_steps": 147, "total_steps": 153, "loss": 0.5109, "lr": 1.8948725820160662e-07, "epoch": 0.96, "percentage": 96.08, "elapsed_time": "1:53:29", "remaining_time": "0:04:37", "throughput": 45274.24, "total_tokens": 308281344}
+{"current_steps": 148, "total_steps": 153, "loss": 0.5182, "lr": 1.3163925091384533e-07, "epoch": 0.966530612244898, "percentage": 96.73, "elapsed_time": "1:54:15", "remaining_time": "0:03:51", "throughput": 45275.12, "total_tokens": 310378496}
+{"current_steps": 149, "total_steps": 153, "loss": 0.4902, "lr": 8.427576920763958e-08, "epoch": 0.9730612244897959, "percentage": 97.39, "elapsed_time": "1:55:01", "remaining_time": "0:03:05", "throughput": 45277.99, "total_tokens": 312475648}
+{"current_steps": 150, "total_steps": 153, "loss": 0.5019, "lr": 4.741678157389739e-08, "epoch": 0.9795918367346939, "percentage": 98.04, "elapsed_time": "1:55:47", "remaining_time": "0:02:18", "throughput": 45279.73, "total_tokens": 314572800}
+{"current_steps": 151, "total_steps": 153, "loss": 0.5081, "lr": 2.1077827798404726e-08, "epoch": 0.9861224489795918, "percentage": 98.69, "elapsed_time": "1:56:33", "remaining_time": "0:01:32", "throughput": 45278.6, "total_tokens": 316669952}
+{"current_steps": 152, "total_steps": 153, "loss": 0.4872, "lr": 5.270012410216185e-09, "epoch": 0.9926530612244898, "percentage": 99.35, "elapsed_time": "1:57:20", "remaining_time": "0:00:46", "throughput": 45277.7, "total_tokens": 318767104}
+{"current_steps": 153, "total_steps": 153, "loss": 0.4965, "lr": 0.0, "epoch": 0.9991836734693877, "percentage": 100.0, "elapsed_time": "1:58:06", "remaining_time": "0:00:00", "throughput": 45276.85, "total_tokens": 320864256}
+{"current_steps": 153, "total_steps": 153, "epoch": 0.9991836734693877, "percentage": 100.0, "elapsed_time": "1:58:28", "remaining_time": "0:00:00", "throughput": 45135.47, "total_tokens": 320864256}

trainer_state.json

@@ -0,0 +1,1267 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9991836734693877,
+  "eval_steps": 500,
+  "global_step": 153,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006530612244897959,
+      "grad_norm": 0.6802010536193848,
+      "learning_rate": 4.999472998758978e-05,
+      "loss": 0.7016,
+      "num_input_tokens_seen": 2097152,
+      "step": 1
+    },
+    {
+      "epoch": 0.013061224489795919,
+      "grad_norm": 0.6286860704421997,
+      "learning_rate": 4.99789221722016e-05,
+      "loss": 0.6549,
+      "num_input_tokens_seen": 4194304,
+      "step": 2
+    },
+    {
+      "epoch": 0.019591836734693877,
+      "grad_norm": 0.5965273976325989,
+      "learning_rate": 4.995258321842611e-05,
+      "loss": 0.6414,
+      "num_input_tokens_seen": 6291456,
+      "step": 3
+    },
+    {
+      "epoch": 0.026122448979591838,
+      "grad_norm": 0.513691782951355,
+      "learning_rate": 4.991572423079236e-05,
+      "loss": 0.6061,
+      "num_input_tokens_seen": 8388608,
+      "step": 4
+    },
+    {
+      "epoch": 0.0326530612244898,
+      "grad_norm": 0.5384091138839722,
+      "learning_rate": 4.986836074908616e-05,
+      "loss": 0.6026,
+      "num_input_tokens_seen": 10485760,
+      "step": 5
+    },
+    {
+      "epoch": 0.03918367346938775,
+      "grad_norm": 0.48317599296569824,
+      "learning_rate": 4.98105127417984e-05,
+      "loss": 0.5596,
+      "num_input_tokens_seen": 12582912,
+      "step": 6
+    },
+    {
+      "epoch": 0.045714285714285714,
+      "grad_norm": 0.35217732191085815,
+      "learning_rate": 4.974220459770639e-05,
+      "loss": 0.557,
+      "num_input_tokens_seen": 14680064,
+      "step": 7
+    },
+    {
+      "epoch": 0.052244897959183675,
+      "grad_norm": 0.15410029888153076,
+      "learning_rate": 4.966346511559149e-05,
+      "loss": 0.5416,
+      "num_input_tokens_seen": 16777216,
+      "step": 8
+    },
+    {
+      "epoch": 0.05877551020408163,
+      "grad_norm": 0.10962219536304474,
+      "learning_rate": 4.957432749209755e-05,
+      "loss": 0.5424,
+      "num_input_tokens_seen": 18874368,
+      "step": 9
+    },
+    {
+      "epoch": 0.0653061224489796,
+      "grad_norm": 0.0843987911939621,
+      "learning_rate": 4.9474829307735115e-05,
+      "loss": 0.5242,
+      "num_input_tokens_seen": 20971520,
+      "step": 10
+    },
+    {
+      "epoch": 0.07183673469387755,
+      "grad_norm": 0.06282058358192444,
+      "learning_rate": 4.9365012511037514e-05,
+      "loss": 0.5195,
+      "num_input_tokens_seen": 23068672,
+      "step": 11
+    },
+    {
+      "epoch": 0.0783673469387755,
+      "grad_norm": 0.05317516624927521,
+      "learning_rate": 4.9244923400875245e-05,
+      "loss": 0.5259,
+      "num_input_tokens_seen": 25165824,
+      "step": 12
+    },
+    {
+      "epoch": 0.08489795918367347,
+      "grad_norm": 0.04503787308931351,
+      "learning_rate": 4.911461260693638e-05,
+      "loss": 0.521,
+      "num_input_tokens_seen": 27262976,
+      "step": 13
+    },
+    {
+      "epoch": 0.09142857142857143,
+      "grad_norm": 0.040327247232198715,
+      "learning_rate": 4.8974135068381036e-05,
+      "loss": 0.5269,
+      "num_input_tokens_seen": 29360128,
+      "step": 14
+    },
+    {
+      "epoch": 0.09795918367346938,
+      "grad_norm": 0.03843770548701286,
+      "learning_rate": 4.882355001067892e-05,
+      "loss": 0.5208,
+      "num_input_tokens_seen": 31457280,
+      "step": 15
+    },
+    {
+      "epoch": 0.10448979591836735,
+      "grad_norm": 0.03380432352423668,
+      "learning_rate": 4.8662920920639866e-05,
+      "loss": 0.5193,
+      "num_input_tokens_seen": 33554432,
+      "step": 16
+    },
+    {
+      "epoch": 0.1110204081632653,
+      "grad_norm": 0.031558409333229065,
+      "learning_rate": 4.849231551964771e-05,
+      "loss": 0.4995,
+      "num_input_tokens_seen": 35651584,
+      "step": 17
+    },
+    {
+      "epoch": 0.11755102040816326,
+      "grad_norm": 0.031164532527327538,
+      "learning_rate": 4.8311805735108894e-05,
+      "loss": 0.5277,
+      "num_input_tokens_seen": 37748736,
+      "step": 18
+    },
+    {
+      "epoch": 0.12408163265306123,
+      "grad_norm": 0.030629999935626984,
+      "learning_rate": 4.81214676701278e-05,
+      "loss": 0.5187,
+      "num_input_tokens_seen": 39845888,
+      "step": 19
+    },
+    {
+      "epoch": 0.1306122448979592,
+      "grad_norm": 0.028932394459843636,
+      "learning_rate": 4.792138157142158e-05,
+      "loss": 0.5322,
+      "num_input_tokens_seen": 41943040,
+      "step": 20
+    },
+    {
+      "epoch": 0.13714285714285715,
+      "grad_norm": 0.027270587161183357,
+      "learning_rate": 4.7711631795488096e-05,
+      "loss": 0.4978,
+      "num_input_tokens_seen": 44040192,
+      "step": 21
+    },
+    {
+      "epoch": 0.1436734693877551,
+      "grad_norm": 0.027742592617869377,
+      "learning_rate": 4.749230677304114e-05,
+      "loss": 0.5253,
+      "num_input_tokens_seen": 46137344,
+      "step": 22
+    },
+    {
+      "epoch": 0.15020408163265306,
+      "grad_norm": 0.027034137398004532,
+      "learning_rate": 4.726349897172791e-05,
+      "loss": 0.5309,
+      "num_input_tokens_seen": 48234496,
+      "step": 23
+    },
+    {
+      "epoch": 0.156734693877551,
+      "grad_norm": 0.026147669181227684,
+      "learning_rate": 4.702530485714461e-05,
+      "loss": 0.5197,
+      "num_input_tokens_seen": 50331648,
+      "step": 24
+    },
+    {
+      "epoch": 0.16326530612244897,
+      "grad_norm": 0.025035962462425232,
+      "learning_rate": 4.677782485216644e-05,
+      "loss": 0.5115,
+      "num_input_tokens_seen": 52428800,
+      "step": 25
+    },
+    {
+      "epoch": 0.16979591836734695,
+      "grad_norm": 0.024556027725338936,
+      "learning_rate": 4.6521163294609196e-05,
+      "loss": 0.4952,
+      "num_input_tokens_seen": 54525952,
+      "step": 26
+    },
+    {
+      "epoch": 0.1763265306122449,
+      "grad_norm": 0.02424173429608345,
+      "learning_rate": 4.625542839324036e-05,
+      "loss": 0.4781,
+      "num_input_tokens_seen": 56623104,
+      "step": 27
+    },
+    {
+      "epoch": 0.18285714285714286,
+      "grad_norm": 0.02580653876066208,
+      "learning_rate": 4.598073218215817e-05,
+      "loss": 0.5067,
+      "num_input_tokens_seen": 58720256,
+      "step": 28
+    },
+    {
+      "epoch": 0.1893877551020408,
+      "grad_norm": 0.024303199723362923,
+      "learning_rate": 4.5697190473557946e-05,
+      "loss": 0.514,
+      "num_input_tokens_seen": 60817408,
+      "step": 29
+    },
+    {
+      "epoch": 0.19591836734693877,
+      "grad_norm": 0.02427365817129612,
+      "learning_rate": 4.540492280890555e-05,
+      "loss": 0.5062,
+      "num_input_tokens_seen": 62914560,
+      "step": 30
+    },
+    {
+      "epoch": 0.20244897959183675,
+      "grad_norm": 0.023720987141132355,
+      "learning_rate": 4.510405240853854e-05,
+      "loss": 0.494,
+      "num_input_tokens_seen": 65011712,
+      "step": 31
+    },
+    {
+      "epoch": 0.2089795918367347,
+      "grad_norm": 0.0251515731215477,
+      "learning_rate": 4.4794706119716455e-05,
+      "loss": 0.5056,
+      "num_input_tokens_seen": 67108864,
+      "step": 32
+    },
+    {
+      "epoch": 0.21551020408163266,
+      "grad_norm": 0.022940408438444138,
+      "learning_rate": 4.447701436314176e-05,
+      "loss": 0.5128,
+      "num_input_tokens_seen": 69206016,
+      "step": 33
+    },
+    {
+      "epoch": 0.2220408163265306,
+      "grad_norm": 0.023887069895863533,
+      "learning_rate": 4.415111107797445e-05,
+      "loss": 0.5024,
+      "num_input_tokens_seen": 71303168,
+      "step": 34
+    },
+    {
+      "epoch": 0.22857142857142856,
+      "grad_norm": 0.022622637450695038,
+      "learning_rate": 4.381713366536311e-05,
+      "loss": 0.4998,
+      "num_input_tokens_seen": 73400320,
+      "step": 35
+    },
+    {
+      "epoch": 0.23510204081632652,
+      "grad_norm": 0.02263909950852394,
+      "learning_rate": 4.347522293051648e-05,
+      "loss": 0.5222,
+      "num_input_tokens_seen": 75497472,
+      "step": 36
+    },
+    {
+      "epoch": 0.2416326530612245,
+      "grad_norm": 0.023353304713964462,
+      "learning_rate": 4.312552302333982e-05,
+      "loss": 0.501,
+      "num_input_tokens_seen": 77594624,
+      "step": 37
+    },
+    {
+      "epoch": 0.24816326530612245,
+      "grad_norm": 0.02225712686777115,
+      "learning_rate": 4.276818137766118e-05,
+      "loss": 0.5035,
+      "num_input_tokens_seen": 79691776,
+      "step": 38
+    },
+    {
+      "epoch": 0.2546938775510204,
+      "grad_norm": 0.022769000381231308,
+      "learning_rate": 4.2403348649073174e-05,
+      "loss": 0.5115,
+      "num_input_tokens_seen": 81788928,
+      "step": 39
+    },
+    {
+      "epoch": 0.2612244897959184,
+      "grad_norm": 0.0222884863615036,
+      "learning_rate": 4.203117865141635e-05,
+      "loss": 0.5087,
+      "num_input_tokens_seen": 83886080,
+      "step": 40
+    },
+    {
+      "epoch": 0.2677551020408163,
+      "grad_norm": 0.02289729192852974,
+      "learning_rate": 4.1651828291931264e-05,
+      "loss": 0.5095,
+      "num_input_tokens_seen": 85983232,
+      "step": 41
+    },
+    {
+      "epoch": 0.2742857142857143,
+      "grad_norm": 0.023385386914014816,
+      "learning_rate": 4.126545750510605e-05,
+      "loss": 0.5033,
+      "num_input_tokens_seen": 88080384,
+      "step": 42
+    },
+    {
+      "epoch": 0.2808163265306122,
+      "grad_norm": 0.02286476455628872,
+      "learning_rate": 4.0872229185248075e-05,
+      "loss": 0.5245,
+      "num_input_tokens_seen": 90177536,
+      "step": 43
+    },
+    {
+      "epoch": 0.2873469387755102,
+      "grad_norm": 0.02207457832992077,
+      "learning_rate": 4.047230911780737e-05,
+      "loss": 0.5041,
+      "num_input_tokens_seen": 92274688,
+      "step": 44
+    },
+    {
+      "epoch": 0.2938775510204082,
+      "grad_norm": 0.021405808627605438,
+      "learning_rate": 4.0065865909481417e-05,
+      "loss": 0.4929,
+      "num_input_tokens_seen": 94371840,
+      "step": 45
+    },
+    {
+      "epoch": 0.3004081632653061,
+      "grad_norm": 0.022242728620767593,
+      "learning_rate": 3.965307091713037e-05,
+      "loss": 0.4939,
+      "num_input_tokens_seen": 96468992,
+      "step": 46
+    },
+    {
+      "epoch": 0.3069387755102041,
+      "grad_norm": 0.02234838157892227,
+      "learning_rate": 3.923409817553284e-05,
+      "loss": 0.5008,
+      "num_input_tokens_seen": 98566144,
+      "step": 47
+    },
+    {
+      "epoch": 0.313469387755102,
+      "grad_norm": 0.020911742001771927,
+      "learning_rate": 3.880912432401265e-05,
+      "loss": 0.5023,
+      "num_input_tokens_seen": 100663296,
+      "step": 48
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.02207380160689354,
+      "learning_rate": 3.837832853196751e-05,
+      "loss": 0.5124,
+      "num_input_tokens_seen": 102760448,
+      "step": 49
+    },
+    {
+      "epoch": 0.32653061224489793,
+      "grad_norm": 0.021706702187657356,
+      "learning_rate": 3.794189242333106e-05,
+      "loss": 0.5033,
+      "num_input_tokens_seen": 104857600,
+      "step": 50
+    },
+    {
+      "epoch": 0.3330612244897959,
+      "grad_norm": 0.02188958041369915,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.4958,
+      "num_input_tokens_seen": 106954752,
+      "step": 51
+    },
+    {
+      "epoch": 0.3395918367346939,
+      "grad_norm": 0.02165570855140686,
+      "learning_rate": 3.705283756425872e-05,
+      "loss": 0.5006,
+      "num_input_tokens_seen": 109051904,
+      "step": 52
+    },
+    {
+      "epoch": 0.3461224489795918,
+      "grad_norm": 0.02152332104742527,
+      "learning_rate": 3.6600593640234086e-05,
+      "loss": 0.5033,
+      "num_input_tokens_seen": 111149056,
+      "step": 53
+    },
+    {
+      "epoch": 0.3526530612244898,
+      "grad_norm": 0.02067963406443596,
+      "learning_rate": 3.6143458894413465e-05,
+      "loss": 0.5038,
+      "num_input_tokens_seen": 113246208,
+      "step": 54
+    },
+    {
+      "epoch": 0.35918367346938773,
+      "grad_norm": 0.02125193364918232,
+      "learning_rate": 3.568162605525953e-05,
+      "loss": 0.4973,
+      "num_input_tokens_seen": 115343360,
+      "step": 55
+    },
+    {
+      "epoch": 0.3657142857142857,
+      "grad_norm": 0.020537488162517548,
+      "learning_rate": 3.5215289831955786e-05,
+      "loss": 0.495,
+      "num_input_tokens_seen": 117440512,
+      "step": 56
+    },
+    {
+      "epoch": 0.3722448979591837,
+      "grad_norm": 0.021631518378853798,
+      "learning_rate": 3.474464683231698e-05,
+      "loss": 0.4971,
+      "num_input_tokens_seen": 119537664,
+      "step": 57
+    },
+    {
+      "epoch": 0.3787755102040816,
+      "grad_norm": 0.023077189922332764,
+      "learning_rate": 3.426989547989902e-05,
+      "loss": 0.5412,
+      "num_input_tokens_seen": 121634816,
+      "step": 58
+    },
+    {
+      "epoch": 0.3853061224489796,
+      "grad_norm": 0.02074201963841915,
+      "learning_rate": 3.379123593034342e-05,
+      "loss": 0.5219,
+      "num_input_tokens_seen": 123731968,
+      "step": 59
+    },
+    {
+      "epoch": 0.39183673469387753,
+      "grad_norm": 0.021061761304736137,
+      "learning_rate": 3.330886998699149e-05,
+      "loss": 0.4989,
+      "num_input_tokens_seen": 125829120,
+      "step": 60
+    },
+    {
+      "epoch": 0.3983673469387755,
+      "grad_norm": 0.021866271272301674,
+      "learning_rate": 3.282300101580386e-05,
+      "loss": 0.5122,
+      "num_input_tokens_seen": 127926272,
+      "step": 61
+    },
+    {
+      "epoch": 0.4048979591836735,
+      "grad_norm": 0.020894547924399376,
+      "learning_rate": 3.2333833859621153e-05,
+      "loss": 0.4987,
+      "num_input_tokens_seen": 130023424,
+      "step": 62
+    },
+    {
+      "epoch": 0.4114285714285714,
+      "grad_norm": 0.020912354812026024,
+      "learning_rate": 3.1841574751802076e-05,
+      "loss": 0.4968,
+      "num_input_tokens_seen": 132120576,
+      "step": 63
+    },
+    {
+      "epoch": 0.4179591836734694,
+      "grad_norm": 0.02170964516699314,
+      "learning_rate": 3.13464312292752e-05,
+      "loss": 0.499,
+      "num_input_tokens_seen": 134217728,
+      "step": 64
+    },
+    {
+      "epoch": 0.42448979591836733,
+      "grad_norm": 0.020900549367070198,
+      "learning_rate": 3.084861204504122e-05,
+      "loss": 0.5055,
+      "num_input_tokens_seen": 136314880,
+      "step": 65
+    },
+    {
+      "epoch": 0.4310204081632653,
+      "grad_norm": 0.020687857642769814,
+      "learning_rate": 3.0348327080162435e-05,
+      "loss": 0.5014,
+      "num_input_tokens_seen": 138412032,
+      "step": 66
+    },
+    {
+      "epoch": 0.43755102040816324,
+      "grad_norm": 0.02071143500506878,
+      "learning_rate": 2.9845787255276753e-05,
+      "loss": 0.4892,
+      "num_input_tokens_seen": 140509184,
+      "step": 67
+    },
+    {
+      "epoch": 0.4440816326530612,
+      "grad_norm": 0.021139299497008324,
+      "learning_rate": 2.9341204441673266e-05,
+      "loss": 0.5069,
+      "num_input_tokens_seen": 142606336,
+      "step": 68
+    },
+    {
+      "epoch": 0.4506122448979592,
+      "grad_norm": 0.020430322736501694,
+      "learning_rate": 2.8834791371967142e-05,
+      "loss": 0.4988,
+      "num_input_tokens_seen": 144703488,
+      "step": 69
+    },
+    {
+      "epoch": 0.45714285714285713,
+      "grad_norm": 0.020096473395824432,
+      "learning_rate": 2.8326761550411345e-05,
+      "loss": 0.4771,
+      "num_input_tokens_seen": 146800640,
+      "step": 70
+    },
+    {
+      "epoch": 0.4636734693877551,
+      "grad_norm": 0.020946258679032326,
+      "learning_rate": 2.781732916288303e-05,
+      "loss": 0.5036,
+      "num_input_tokens_seen": 148897792,
+      "step": 71
+    },
+    {
+      "epoch": 0.47020408163265304,
+      "grad_norm": 0.019651729613542557,
+      "learning_rate": 2.7306708986582553e-05,
+      "loss": 0.499,
+      "num_input_tokens_seen": 150994944,
+      "step": 72
+    },
+    {
+      "epoch": 0.476734693877551,
+      "grad_norm": 0.020175347104668617,
+      "learning_rate": 2.679511629948319e-05,
+      "loss": 0.5067,
+      "num_input_tokens_seen": 153092096,
+      "step": 73
+    },
+    {
+      "epoch": 0.483265306122449,
+      "grad_norm": 0.02037941850721836,
+      "learning_rate": 2.628276678956974e-05,
+      "loss": 0.5015,
+      "num_input_tokens_seen": 155189248,
+      "step": 74
+    },
+    {
+      "epoch": 0.4897959183673469,
+      "grad_norm": 0.020525282248854637,
+      "learning_rate": 2.5769876463904265e-05,
+      "loss": 0.504,
+      "num_input_tokens_seen": 157286400,
+      "step": 75
+    },
+    {
+      "epoch": 0.4963265306122449,
+      "grad_norm": 0.02100261114537716,
+      "learning_rate": 2.5256661557557247e-05,
+      "loss": 0.513,
+      "num_input_tokens_seen": 159383552,
+      "step": 76
+    },
+    {
+      "epoch": 0.5028571428571429,
+      "grad_norm": 0.02081277035176754,
+      "learning_rate": 2.4743338442442755e-05,
+      "loss": 0.5093,
+      "num_input_tokens_seen": 161480704,
+      "step": 77
+    },
+    {
+      "epoch": 0.5093877551020408,
+      "grad_norm": 0.01962732896208763,
+      "learning_rate": 2.4230123536095748e-05,
+      "loss": 0.475,
+      "num_input_tokens_seen": 163577856,
+      "step": 78
+    },
+    {
+      "epoch": 0.5159183673469387,
+      "grad_norm": 0.020476974546909332,
+      "learning_rate": 2.3717233210430256e-05,
+      "loss": 0.4827,
+      "num_input_tokens_seen": 165675008,
+      "step": 79
+    },
+    {
+      "epoch": 0.5224489795918368,
+      "grad_norm": 0.02092832699418068,
+      "learning_rate": 2.3204883700516812e-05,
+      "loss": 0.5234,
+      "num_input_tokens_seen": 167772160,
+      "step": 80
+    },
+    {
+      "epoch": 0.5289795918367347,
+      "grad_norm": 0.020366327837109566,
+      "learning_rate": 2.2693291013417453e-05,
+      "loss": 0.5204,
+      "num_input_tokens_seen": 169869312,
+      "step": 81
+    },
+    {
+      "epoch": 0.5355102040816326,
+      "grad_norm": 0.020487571135163307,
+      "learning_rate": 2.2182670837116975e-05,
+      "loss": 0.4886,
+      "num_input_tokens_seen": 171966464,
+      "step": 82
+    },
+    {
+      "epoch": 0.5420408163265306,
+      "grad_norm": 0.01977311633527279,
+      "learning_rate": 2.1673238449588668e-05,
+      "loss": 0.5005,
+      "num_input_tokens_seen": 174063616,
+      "step": 83
+    },
+    {
+      "epoch": 0.5485714285714286,
+      "grad_norm": 0.01979038491845131,
+      "learning_rate": 2.116520862803286e-05,
+      "loss": 0.4832,
+      "num_input_tokens_seen": 176160768,
+      "step": 84
+    },
+    {
+      "epoch": 0.5551020408163265,
+      "grad_norm": 0.020210135728120804,
+      "learning_rate": 2.0658795558326743e-05,
+      "loss": 0.5021,
+      "num_input_tokens_seen": 178257920,
+      "step": 85
+    },
+    {
+      "epoch": 0.5616326530612245,
+      "grad_norm": 0.020240608602762222,
+      "learning_rate": 2.015421274472325e-05,
+      "loss": 0.4839,
+      "num_input_tokens_seen": 180355072,
+      "step": 86
+    },
+    {
+      "epoch": 0.5681632653061225,
+      "grad_norm": 0.020403753966093063,
+      "learning_rate": 1.965167291983757e-05,
+      "loss": 0.5078,
+      "num_input_tokens_seen": 182452224,
+      "step": 87
+    },
+    {
+      "epoch": 0.5746938775510204,
+      "grad_norm": 0.020527003332972527,
+      "learning_rate": 1.9151387954958794e-05,
+      "loss": 0.4981,
+      "num_input_tokens_seen": 184549376,
+      "step": 88
+    },
+    {
+      "epoch": 0.5812244897959183,
+      "grad_norm": 0.02056964300572872,
+      "learning_rate": 1.8653568770724806e-05,
+      "loss": 0.4913,
+      "num_input_tokens_seen": 186646528,
+      "step": 89
+    },
+    {
+      "epoch": 0.5877551020408164,
+      "grad_norm": 0.019625499844551086,
+      "learning_rate": 1.815842524819793e-05,
+      "loss": 0.4862,
+      "num_input_tokens_seen": 188743680,
+      "step": 90
+    },
+    {
+      "epoch": 0.5942857142857143,
+      "grad_norm": 0.02040235698223114,
+      "learning_rate": 1.7666166140378852e-05,
+      "loss": 0.5146,
+      "num_input_tokens_seen": 190840832,
+      "step": 91
+    },
+    {
+      "epoch": 0.6008163265306122,
+      "grad_norm": 0.02010432258248329,
+      "learning_rate": 1.7176998984196146e-05,
+      "loss": 0.4952,
+      "num_input_tokens_seen": 192937984,
+      "step": 92
+    },
+    {
+      "epoch": 0.6073469387755102,
+      "grad_norm": 0.01999637298285961,
+      "learning_rate": 1.6691130013008514e-05,
+      "loss": 0.4845,
+      "num_input_tokens_seen": 195035136,
+      "step": 93
+    },
+    {
+      "epoch": 0.6138775510204082,
+      "grad_norm": 0.019539078697562218,
+      "learning_rate": 1.620876406965658e-05,
+      "loss": 0.4881,
+      "num_input_tokens_seen": 197132288,
+      "step": 94
+    },
+    {
+      "epoch": 0.6204081632653061,
+      "grad_norm": 0.020548058673739433,
+      "learning_rate": 1.5730104520100982e-05,
+      "loss": 0.498,
+      "num_input_tokens_seen": 199229440,
+      "step": 95
+    },
+    {
+      "epoch": 0.626938775510204,
+      "grad_norm": 0.020467426627874374,
+      "learning_rate": 1.5255353167683017e-05,
+      "loss": 0.4989,
+      "num_input_tokens_seen": 201326592,
+      "step": 96
+    },
+    {
+      "epoch": 0.6334693877551021,
+      "grad_norm": 0.019751951098442078,
+      "learning_rate": 1.4784710168044213e-05,
+      "loss": 0.4941,
+      "num_input_tokens_seen": 203423744,
+      "step": 97
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.01974237710237503,
+      "learning_rate": 1.4318373944740484e-05,
+      "loss": 0.4919,
+      "num_input_tokens_seen": 205520896,
+      "step": 98
+    },
+    {
+      "epoch": 0.6465306122448979,
+      "grad_norm": 0.019516095519065857,
+      "learning_rate": 1.3856541105586545e-05,
+      "loss": 0.5047,
+      "num_input_tokens_seen": 207618048,
+      "step": 99
+    },
+    {
+      "epoch": 0.6530612244897959,
+      "grad_norm": 0.01965564861893654,
+      "learning_rate": 1.339940635976592e-05,
+      "loss": 0.5104,
+      "num_input_tokens_seen": 209715200,
+      "step": 100
+    },
+    {
+      "epoch": 0.6595918367346939,
+      "grad_norm": 0.019674964249134064,
+      "learning_rate": 1.2947162435741278e-05,
+      "loss": 0.5008,
+      "num_input_tokens_seen": 211812352,
+      "step": 101
+    },
+    {
+      "epoch": 0.6661224489795918,
+      "grad_norm": 0.019747601822018623,
+      "learning_rate": 1.2500000000000006e-05,
+      "loss": 0.5022,
+      "num_input_tokens_seen": 213909504,
+      "step": 102
+    },
+    {
+      "epoch": 0.6726530612244898,
+      "grad_norm": 0.0198560431599617,
+      "learning_rate": 1.205810757666894e-05,
+      "loss": 0.4979,
+      "num_input_tokens_seen": 216006656,
+      "step": 103
+    },
+    {
+      "epoch": 0.6791836734693878,
+      "grad_norm": 0.020007461309432983,
+      "learning_rate": 1.1621671468032493e-05,
+      "loss": 0.4972,
+      "num_input_tokens_seen": 218103808,
+      "step": 104
+    },
+    {
+      "epoch": 0.6857142857142857,
+      "grad_norm": 0.019895223900675774,
+      "learning_rate": 1.1190875675987356e-05,
+      "loss": 0.5058,
+      "num_input_tokens_seen": 220200960,
+      "step": 105
+    },
+    {
+      "epoch": 0.6922448979591836,
+      "grad_norm": 0.019599556922912598,
+      "learning_rate": 1.0765901824467167e-05,
+      "loss": 0.4935,
+      "num_input_tokens_seen": 222298112,
+      "step": 106
+    },
+    {
+      "epoch": 0.6987755102040817,
+      "grad_norm": 0.019807366654276848,
+      "learning_rate": 1.0346929082869641e-05,
+      "loss": 0.5041,
+      "num_input_tokens_seen": 224395264,
+      "step": 107
+    },
+    {
+      "epoch": 0.7053061224489796,
+      "grad_norm": 0.019651690497994423,
+      "learning_rate": 9.934134090518593e-06,
+      "loss": 0.5066,
+      "num_input_tokens_seen": 226492416,
+      "step": 108
+    },
+    {
+      "epoch": 0.7118367346938775,
+      "grad_norm": 0.020175212994217873,
+      "learning_rate": 9.527690882192636e-06,
+      "loss": 0.5181,
+      "num_input_tokens_seen": 228589568,
+      "step": 109
+    },
+    {
+      "epoch": 0.7183673469387755,
+      "grad_norm": 0.021520880982279778,
+      "learning_rate": 9.127770814751933e-06,
+      "loss": 0.4877,
+      "num_input_tokens_seen": 230686720,
+      "step": 110
+    },
+    {
+      "epoch": 0.7248979591836735,
+      "grad_norm": 0.02041519619524479,
+      "learning_rate": 8.734542494893955e-06,
+      "loss": 0.4886,
+      "num_input_tokens_seen": 232783872,
+      "step": 111
+    },
+    {
+      "epoch": 0.7314285714285714,
+      "grad_norm": 0.020032085478305817,
+      "learning_rate": 8.348171708068747e-06,
+      "loss": 0.4986,
+      "num_input_tokens_seen": 234881024,
+      "step": 112
+    },
+    {
+      "epoch": 0.7379591836734694,
+      "grad_norm": 0.01945379003882408,
+      "learning_rate": 7.968821348583644e-06,
+      "loss": 0.4892,
+      "num_input_tokens_seen": 236978176,
+      "step": 113
+    },
+    {
+      "epoch": 0.7444897959183674,
+      "grad_norm": 0.019653445109725,
+      "learning_rate": 7.5966513509268365e-06,
+      "loss": 0.5048,
+      "num_input_tokens_seen": 239075328,
+      "step": 114
+    },
+    {
+      "epoch": 0.7510204081632653,
+      "grad_norm": 0.020067734643816948,
+      "learning_rate": 7.231818622338823e-06,
+      "loss": 0.4907,
+      "num_input_tokens_seen": 241172480,
+      "step": 115
+    },
+    {
+      "epoch": 0.7575510204081632,
+      "grad_norm": 0.0194945577532053,
+      "learning_rate": 6.8744769766601854e-06,
+      "loss": 0.5074,
+      "num_input_tokens_seen": 243269632,
+      "step": 116
+    },
+    {
+      "epoch": 0.7640816326530612,
+      "grad_norm": 0.019672313705086708,
+      "learning_rate": 6.524777069483526e-06,
+      "loss": 0.4954,
+      "num_input_tokens_seen": 245366784,
+      "step": 117
+    },
+    {
+      "epoch": 0.7706122448979592,
+      "grad_norm": 0.019437000155448914,
+      "learning_rate": 6.182866334636889e-06,
+      "loss": 0.5036,
+      "num_input_tokens_seen": 247463936,
+      "step": 118
+    },
+    {
+      "epoch": 0.7771428571428571,
+      "grad_norm": 0.020035067573189735,
+      "learning_rate": 5.848888922025553e-06,
+      "loss": 0.5133,
+      "num_input_tokens_seen": 249561088,
+      "step": 119
+    },
+    {
+      "epoch": 0.7836734693877551,
+      "grad_norm": 0.019359605386853218,
+      "learning_rate": 5.522985636858239e-06,
+      "loss": 0.4965,
+      "num_input_tokens_seen": 251658240,
+      "step": 120
+    },
+    {
+      "epoch": 0.7902040816326531,
+      "grad_norm": 0.01978667639195919,
+      "learning_rate": 5.205293880283552e-06,
+      "loss": 0.5068,
+      "num_input_tokens_seen": 253755392,
+      "step": 121
+    },
+    {
+      "epoch": 0.796734693877551,
+      "grad_norm": 0.019405698403716087,
+      "learning_rate": 4.8959475914614554e-06,
+      "loss": 0.4993,
+      "num_input_tokens_seen": 255852544,
+      "step": 122
+    },
+    {
+      "epoch": 0.803265306122449,
+      "grad_norm": 0.01977471075952053,
+      "learning_rate": 4.5950771910944605e-06,
+      "loss": 0.5173,
+      "num_input_tokens_seen": 257949696,
+      "step": 123
+    },
+    {
+      "epoch": 0.809795918367347,
+      "grad_norm": 0.01949562318623066,
+      "learning_rate": 4.3028095264420535e-06,
+      "loss": 0.5032,
+      "num_input_tokens_seen": 260046848,
+      "step": 124
+    },
+    {
+      "epoch": 0.8163265306122449,
+      "grad_norm": 0.019873222336173058,
+      "learning_rate": 4.019267817841835e-06,
+      "loss": 0.505,
+      "num_input_tokens_seen": 262144000,
+      "step": 125
+    },
+    {
+      "epoch": 0.8228571428571428,
+      "grad_norm": 0.019852887839078903,
+      "learning_rate": 3.7445716067596503e-06,
+      "loss": 0.5145,
+      "num_input_tokens_seen": 264241152,
+      "step": 126
+    },
+    {
+      "epoch": 0.8293877551020408,
+      "grad_norm": 0.019747605547308922,
+      "learning_rate": 3.478836705390809e-06,
+      "loss": 0.4967,
+      "num_input_tokens_seen": 266338304,
+      "step": 127
+    },
+    {
+      "epoch": 0.8359183673469388,
+      "grad_norm": 0.019296282902359962,
+      "learning_rate": 3.222175147833556e-06,
+      "loss": 0.5001,
+      "num_input_tokens_seen": 268435456,
+      "step": 128
+    },
+    {
+      "epoch": 0.8424489795918367,
+      "grad_norm": 0.020198358222842216,
+      "learning_rate": 2.974695142855388e-06,
+      "loss": 0.5037,
+      "num_input_tokens_seen": 270532608,
+      "step": 129
+    },
+    {
+      "epoch": 0.8489795918367347,
+      "grad_norm": 0.020021170377731323,
+      "learning_rate": 2.7365010282720952e-06,
+      "loss": 0.5238,
+      "num_input_tokens_seen": 272629760,
+      "step": 130
+    },
+    {
+      "epoch": 0.8555102040816327,
+      "grad_norm": 0.019700711593031883,
+      "learning_rate": 2.507693226958871e-06,
+      "loss": 0.5007,
+      "num_input_tokens_seen": 274726912,
+      "step": 131
+    },
+    {
+      "epoch": 0.8620408163265306,
+      "grad_norm": 0.019315095618367195,
+      "learning_rate": 2.2883682045119063e-06,
+      "loss": 0.5119,
+      "num_input_tokens_seen": 276824064,
+      "step": 132
+    },
+    {
+      "epoch": 0.8685714285714285,
+      "grad_norm": 0.02047501504421234,
+      "learning_rate": 2.0786184285784297e-06,
+      "loss": 0.4874,
+      "num_input_tokens_seen": 278921216,
+      "step": 133
+    },
+    {
+      "epoch": 0.8751020408163265,
+      "grad_norm": 0.019602535292506218,
+      "learning_rate": 1.8785323298722097e-06,
+      "loss": 0.4969,
+      "num_input_tokens_seen": 281018368,
+      "step": 134
+    },
+    {
+      "epoch": 0.8816326530612245,
+      "grad_norm": 0.019447464495897293,
+      "learning_rate": 1.6881942648911076e-06,
+      "loss": 0.4835,
+      "num_input_tokens_seen": 283115520,
+      "step": 135
+    },
+    {
+      "epoch": 0.8881632653061224,
+      "grad_norm": 0.0193500854074955,
+      "learning_rate": 1.5076844803522922e-06,
+      "loss": 0.4863,
+      "num_input_tokens_seen": 285212672,
+      "step": 136
+    },
+    {
+      "epoch": 0.8946938775510204,
+      "grad_norm": 0.019578518345952034,
+      "learning_rate": 1.3370790793601373e-06,
+      "loss": 0.5046,
+      "num_input_tokens_seen": 287309824,
+      "step": 137
+    },
+    {
+      "epoch": 0.9012244897959184,
+      "grad_norm": 0.020458122715353966,
+      "learning_rate": 1.1764499893210878e-06,
+      "loss": 0.5018,
+      "num_input_tokens_seen": 289406976,
+      "step": 138
+    },
+    {
+      "epoch": 0.9077551020408163,
+      "grad_norm": 0.019856926053762436,
+      "learning_rate": 1.0258649316189722e-06,
+      "loss": 0.5025,
+      "num_input_tokens_seen": 291504128,
+      "step": 139
+    },
+    {
+      "epoch": 0.9142857142857143,
+      "grad_norm": 0.019992457702755928,
+      "learning_rate": 8.85387393063622e-07,
+      "loss": 0.5139,
+      "num_input_tokens_seen": 293601280,
+      "step": 140
+    },
+    {
+      "epoch": 0.9208163265306123,
+      "grad_norm": 0.019166303798556328,
+      "learning_rate": 7.550765991247654e-07,
+      "loss": 0.484,
+      "num_input_tokens_seen": 295698432,
+      "step": 141
+    },
+    {
+      "epoch": 0.9273469387755102,
+      "grad_norm": 0.019759617745876312,
+      "learning_rate": 6.349874889624962e-07,
+      "loss": 0.5127,
+      "num_input_tokens_seen": 297795584,
+      "step": 142
+    },
+    {
+      "epoch": 0.9338775510204081,
+      "grad_norm": 0.019604109227657318,
+      "learning_rate": 5.25170692264887e-07,
+      "loss": 0.4876,
+      "num_input_tokens_seen": 299892736,
+      "step": 143
+    },
+    {
+      "epoch": 0.9404081632653061,
+      "grad_norm": 0.019114624708890915,
+      "learning_rate": 4.256725079024554e-07,
+      "loss": 0.4925,
+      "num_input_tokens_seen": 301989888,
+      "step": 144
+    },
+    {
+      "epoch": 0.9469387755102041,
+      "grad_norm": 0.019426511600613594,
+      "learning_rate": 3.3653488440851255e-07,
+      "loss": 0.4861,
+      "num_input_tokens_seen": 304087040,
+      "step": 145
+    },
+    {
+      "epoch": 0.953469387755102,
+      "grad_norm": 0.019297398626804352,
+      "learning_rate": 2.5779540229361745e-07,
+      "loss": 0.493,
+      "num_input_tokens_seen": 306184192,
+      "step": 146
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.01964535564184189,
+      "learning_rate": 1.8948725820160662e-07,
+      "loss": 0.5109,
+      "num_input_tokens_seen": 308281344,
+      "step": 147
+    },
+    {
+      "epoch": 0.966530612244898,
+      "grad_norm": 0.019757628440856934,
+      "learning_rate": 1.3163925091384533e-07,
+      "loss": 0.5182,
+      "num_input_tokens_seen": 310378496,
+      "step": 148
+    },
+    {
+      "epoch": 0.9730612244897959,
+      "grad_norm": 0.019987070932984352,
+      "learning_rate": 8.427576920763958e-08,
+      "loss": 0.4902,
+      "num_input_tokens_seen": 312475648,
+      "step": 149
+    },
+    {
+      "epoch": 0.9795918367346939,
+      "grad_norm": 0.020403273403644562,
+      "learning_rate": 4.741678157389739e-08,
+      "loss": 0.5019,
+      "num_input_tokens_seen": 314572800,
+      "step": 150
+    },
+    {
+      "epoch": 0.9861224489795918,
+      "grad_norm": 0.0199234988540411,
+      "learning_rate": 2.1077827798404726e-08,
+      "loss": 0.5081,
+      "num_input_tokens_seen": 316669952,
+      "step": 151
+    },
+    {
+      "epoch": 0.9926530612244898,
+      "grad_norm": 0.019740723073482513,
+      "learning_rate": 5.270012410216185e-09,
+      "loss": 0.4872,
+      "num_input_tokens_seen": 318767104,
+      "step": 152
+    },
+    {
+      "epoch": 0.9991836734693877,
+      "grad_norm": 0.01960798352956772,
+      "learning_rate": 0.0,
+      "loss": 0.4965,
+      "num_input_tokens_seen": 320864256,
+      "step": 153
+    },
+    {
+      "epoch": 0.9991836734693877,
+      "num_input_tokens_seen": 320864256,
+      "step": 153,
+      "total_flos": 1.2496254746971079e+19,
+      "train_loss": 0.5089508540490094,
+      "train_runtime": 7110.2315,
+      "train_samples_per_second": 11.018,
+      "train_steps_per_second": 0.022
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 153,
+  "num_input_tokens_seen": 320864256,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.2496254746971079e+19,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:840b272ce7a133b4f630341b0ee445f6f49a4e4b08796d55b22d41c694f16220
+size 5688