Upload 12 files

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "/workspace/train_gpt2/mistral_backups/new/checkpoint-132000/",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "max_position_embeddings": 512,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.41.0"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1be17a62404ae8883e0d17a4eec54fdffadb48272302755ad59a324a7da4fd53
+size 6485383922

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5affd1d51cdadc1aa86ab45d2e617622fc297b74a7a28378e030d6d9dbe68d5
+size 3242672438

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5cf7652b5b950e75061a3dca6db9ed73f384b6479b013ed74341510032df777
+size 1064

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,82 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.06738393117854495,
+  "eval_steps": 100000000,
+  "global_step": 3000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.246131039284832e-05,
+      "grad_norm": 0.6316260099411011,
+      "learning_rate": 1.0000000000000001e-07,
+      "loss": 2.8261,
+      "step": 1
+    },
+    {
+      "epoch": 0.011230655196424159,
+      "grad_norm": 0.6035754680633545,
+      "learning_rate": 5e-05,
+      "loss": 2.7043,
+      "step": 500
+    },
+    {
+      "epoch": 0.022461310392848318,
+      "grad_norm": 0.5648986101150513,
+      "learning_rate": 4.999825807239274e-05,
+      "loss": 2.7033,
+      "step": 1000
+    },
+    {
+      "epoch": 0.033691965589272475,
+      "grad_norm": 0.5464420914649963,
+      "learning_rate": 4.99930325323159e-05,
+      "loss": 2.6943,
+      "step": 1500
+    },
+    {
+      "epoch": 0.044922620785696636,
+      "grad_norm": 0.5515211820602417,
+      "learning_rate": 4.9984324107970484e-05,
+      "loss": 2.6822,
+      "step": 2000
+    },
+    {
+      "epoch": 0.0561532759821208,
+      "grad_norm": 0.5726838111877441,
+      "learning_rate": 4.9972134012912064e-05,
+      "loss": 2.6746,
+      "step": 2500
+    },
+    {
+      "epoch": 0.06738393117854495,
+      "grad_norm": 0.5756878852844238,
+      "learning_rate": 4.9956463945881706e-05,
+      "loss": 2.6704,
+      "step": 3000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 133563,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 3000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.236054048768e+18,
+  "train_batch_size": 12,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:065ebb10f7f1fa4e4d5e3bf0f21f456da189b06345fcfc9a69be6e3a85f3e79e
+size 5112