Upload 13 files

chat_template.jinja

@@ -0,0 +1 @@
+{% for message in messages %}{{ message.content }}{{ eos_token }}{% endfor %}

config.json

@@ -0,0 +1,38 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "pad_token_id": 50256,
+  "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": {
+    "conversational": {
+      "max_length": 1000
+    }
+  },
+  "transformers_version": "4.56.1",
+  "use_cache": true,
+  "vocab_size": 50257
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": [
+    50256
+  ],
+  "pad_token_id": 50256,
+  "transformers_version": "4.56.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e6128decb2fbbbf2091b5a1043781f01143859b506ad8827f6710c29bc015d7
+size 497774208

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:228440e1d4619f5071feb9c177b65668878048ebf249221f47bb47fd94f19f7e
+size 14645

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62b3d1c6f1c6bcb7321ad7a092bc8ce8309360a9f89dd4f251c8731a98828468
+size 1383

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:844d3b79039378ad71a9875d5099db4b8fd38aeb032a16d37f27724eb21e8869
+size 1465

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,23 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

trainer_state.json

@@ -0,0 +1,146 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 50.0,
+  "eval_steps": 1000,
+  "global_step": 1600,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 3.128,
+      "grad_norm": 23.240234375,
+      "learning_rate": 3.7200000000000004e-06,
+      "loss": 13.8895,
+      "step": 100
+    },
+    {
+      "epoch": 6.256,
+      "grad_norm": 2.89752197265625,
+      "learning_rate": 7.72e-06,
+      "loss": 6.3417,
+      "step": 200
+    },
+    {
+      "epoch": 9.384,
+      "grad_norm": 2.175177812576294,
+      "learning_rate": 1.172e-05,
+      "loss": 4.5781,
+      "step": 300
+    },
+    {
+      "epoch": 12.512,
+      "grad_norm": 1.8080283403396606,
+      "learning_rate": 1.5720000000000002e-05,
+      "loss": 3.9311,
+      "step": 400
+    },
+    {
+      "epoch": 15.64,
+      "grad_norm": 1.8345730304718018,
+      "learning_rate": 1.972e-05,
+      "loss": 3.4845,
+      "step": 500
+    },
+    {
+      "epoch": 18.768,
+      "grad_norm": 1.8004506826400757,
+      "learning_rate": 1.964933244713679e-05,
+      "loss": 3.2046,
+      "step": 600
+    },
+    {
+      "epoch": 21.896,
+      "grad_norm": 1.966347575187683,
+      "learning_rate": 1.851893169061149e-05,
+      "loss": 3.0399,
+      "step": 700
+    },
+    {
+      "epoch": 25.0,
+      "grad_norm": 3.5277066230773926,
+      "learning_rate": 1.66983777525504e-05,
+      "loss": 2.9138,
+      "step": 800
+    },
+    {
+      "epoch": 28.128,
+      "grad_norm": 1.7087632417678833,
+      "learning_rate": 1.4335161085764062e-05,
+      "loss": 2.8223,
+      "step": 900
+    },
+    {
+      "epoch": 31.256,
+      "grad_norm": 1.8053547143936157,
+      "learning_rate": 1.162073545000483e-05,
+      "loss": 2.7583,
+      "step": 1000
+    },
+    {
+      "epoch": 34.384,
+      "grad_norm": 1.9304829835891724,
+      "learning_rate": 8.775007466971067e-06,
+      "loss": 2.7118,
+      "step": 1100
+    },
+    {
+      "epoch": 37.512,
+      "grad_norm": 1.9457958936691284,
+      "learning_rate": 6.028521093652195e-06,
+      "loss": 2.6704,
+      "step": 1200
+    },
+    {
+      "epoch": 40.64,
+      "grad_norm": 1.8289012908935547,
+      "learning_rate": 3.6037803220311184e-06,
+      "loss": 2.6499,
+      "step": 1300
+    },
+    {
+      "epoch": 43.768,
+      "grad_norm": 1.7785428762435913,
+      "learning_rate": 1.697223228935958e-06,
+      "loss": 2.6332,
+      "step": 1400
+    },
+    {
+      "epoch": 46.896,
+      "grad_norm": 1.7786341905593872,
+      "learning_rate": 4.6330773131765484e-07,
+      "loss": 2.6273,
+      "step": 1500
+    },
+    {
+      "epoch": 50.0,
+      "grad_norm": 3.720322608947754,
+      "learning_rate": 1.9983244152199656e-09,
+      "loss": 2.63,
+      "step": 1600
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 1600,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 50,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.30646016e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}