Upload LlamaForCausalLM

config.json

@@ -0,0 +1,157 @@
+{
+  "_name_or_path": "/home/sakbarian/llama/experiments_lora/checkpoint-300",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "best_metric": 1.0994387865066528,
+  "best_model_checkpoint": "experiments_lora/checkpoint-150",
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "epoch": 24.0,
+  "global_step": 150,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.6,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 2.621,
+      "step": 10
+    },
+    {
+      "epoch": 3.2,
+      "learning_rate": 5.9999999999999995e-05,
+      "loss": 2.5081,
+      "step": 20
+    },
+    {
+      "epoch": 4.8,
+      "learning_rate": 8.999999999999999e-05,
+      "loss": 2.2368,
+      "step": 30
+    },
+    {
+      "epoch": 6.4,
+      "learning_rate": 0.00011399999999999999,
+      "loss": 1.6603,
+      "step": 40
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 0.00014399999999999998,
+      "loss": 1.304,
+      "step": 50
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 1.234856128692627,
+      "eval_runtime": 8.6383,
+      "eval_samples_per_second": 23.153,
+      "eval_steps_per_second": 2.894,
+      "step": 50
+    },
+    {
+      "epoch": 9.6,
+      "learning_rate": 0.00017399999999999997,
+      "loss": 1.2076,
+      "step": 60
+    },
+    {
+      "epoch": 11.2,
+      "learning_rate": 0.000204,
+      "loss": 1.1688,
+      "step": 70
+    },
+    {
+      "epoch": 12.8,
+      "learning_rate": 0.000234,
+      "loss": 1.1471,
+      "step": 80
+    },
+    {
+      "epoch": 14.4,
+      "learning_rate": 0.00026399999999999997,
+      "loss": 1.1364,
+      "step": 90
+    },
+    {
+      "epoch": 16.0,
+      "learning_rate": 0.000294,
+      "loss": 1.1284,
+      "step": 100
+    },
+    {
+      "epoch": 16.0,
+      "eval_loss": 1.1279268264770508,
+      "eval_runtime": 8.6373,
+      "eval_samples_per_second": 23.155,
+      "eval_steps_per_second": 2.894,
+      "step": 100
+    },
+    {
+      "epoch": 17.6,
+      "learning_rate": 0.00028799999999999995,
+      "loss": 1.1212,
+      "step": 110
+    },
+    {
+      "epoch": 19.2,
+      "learning_rate": 0.00027299999999999997,
+      "loss": 1.1089,
+      "step": 120
+    },
+    {
+      "epoch": 20.8,
+      "learning_rate": 0.000258,
+      "loss": 1.1044,
+      "step": 130
+    },
+    {
+      "epoch": 22.4,
+      "learning_rate": 0.000243,
+      "loss": 1.082,
+      "step": 140
+    },
+    {
+      "epoch": 24.0,
+      "learning_rate": 0.00022799999999999999,
+      "loss": 1.0521,
+      "step": 150
+    },
+    {
+      "epoch": 24.0,
+      "eval_loss": 1.0994387865066528,
+      "eval_runtime": 8.6221,
+      "eval_samples_per_second": 23.196,
+      "eval_steps_per_second": 2.9,
+      "step": 150
+    }
+  ],
+  "max_position_embeddings": 2048,
+  "max_steps": 300,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_train_epochs": 50,
+  "pad_token_id": 0,
+  "quantization_config": {
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_8bit": true
+  },
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "total_flos": 1.435518270111744e+17,
+  "transformers_version": "4.29.0.dev0",
+  "trial_name": null,
+  "trial_params": null,
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.29.0.dev0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77e3615fd507924cbac5dfa7cccfabc699c0ad44658bcaddb0733a951bd5d865
+size 7000944305