Training in progress, step 500

config.json

@@ -1,45 +1,35 @@
 {
-  "_num_labels": 1,
-  "activation_function": "gelu_new",
   "architectures": [
-    "GPT2LMHeadModel"
+    "LlamaForCausalLM"
   ],
-  "attn_pdrop": 0.1,
-  "bos_token_id": 50256,
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
   "dtype": "float32",
-  "embd_pdrop": 0.1,
-  "eos_token_id": 50256,
-  "id2label": {
-    "0": "LABEL_0"
-  },
+  "eos_token_id": 128001,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
   "initializer_range": 0.02,
-  "label2id": {
-    "LABEL_0": 0
-  },
-  "layer_norm_epsilon": 1e-05,
-  "model_type": "gpt2",
-  "n_ctx": 1024,
-  "n_embd": 768,
-  "n_head": 12,
-  "n_inner": null,
-  "n_layer": 6,
-  "n_positions": 1024,
-  "reorder_and_upcast_attn": false,
-  "resid_pdrop": 0.1,
-  "scale_attn_by_inverse_layer_idx": false,
-  "scale_attn_weights": true,
-  "summary_activation": null,
-  "summary_first_dropout": 0.1,
-  "summary_proj_to_labels": true,
-  "summary_type": "cls_index",
-  "summary_use_proj": true,
-  "task_specific_params": {
-    "text-generation": {
-      "do_sample": true,
-      "max_length": 50
-    }
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
   },
-  "transformers_version": "4.57.0",
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.56.1",
   "use_cache": true,
-  "vocab_size": 50257
+  "vocab_size": 128256
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c25d74c75c99bcaad413b795ddda3884ce7cf6f055c5fe275b99d9c01f45e08
-size 327657928
+oid sha256:7fcd7456718073374938bb8685859dbfc0c97c646e6bfbfca54a44f46dfc27a8
+size 4943274328

runs/Oct13_19-42-14_rigel/events.out.tfevents.1760406137.rigel.646374.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47ef3e41996fb7bd57c86c1fa12d027f5054df85e581893803be4e5ccbc65f65
+size 5410

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1ebc9c95d1a7054cf52bd35f1a4d5a695fafde4677d75bc21a75b8e0c815244
-size 5841
+oid sha256:c444e03c357dbe5b3a337d0a5a6ae59e627ab356ebfb87e30552b9e1fd4cb500
+size 5368