Training in progress, step 2000, checkpoint

checkpoint-2000/config.json

@@ -0,0 +1,33 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "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": 2,
+  "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,
+  "transformers_version": "4.56.1",
+  "use_cache": true,
+  "vocab_size": 30000
+}

checkpoint-2000/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    2
+  ],
+  "pad_token_id": 2,
+  "transformers_version": "4.56.1"
+}

checkpoint-2000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c77b6d9361e5cd40dd36f170897937338c24ae6efff5a743495346b5c6ed97a
+size 435544704

checkpoint-2000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36f92db710a56d3fcf9659527ab3c014339219d2eaa59ad1e883feb967cdca2b
+size 871183627

checkpoint-2000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70fbbf502af306ace3aea43119ceb155de8bc0ae114cdbd35a6e34b7398abb45
+size 14645

checkpoint-2000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4aa03f6e0cd07cf67ce1fbe3101d545f5771ef9148b9debf02b11cf6948da5c
+size 1383

checkpoint-2000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d4501b7d224e0e2f6dd311d12dd6c06f3b041b6e280f4911e44c6801f7714d6
+size 1465

checkpoint-2000/special_tokens_map.json

@@ -0,0 +1,8 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "</s>",
+  "sep_token": "<sep>",
+  "unk_token": "<unk>"
+}

checkpoint-2000/tokenizer_config.json

@@ -0,0 +1,62 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "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
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sep_token": "<sep>",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk>"
+}

checkpoint-2000/trainer_state.json

@@ -0,0 +1,101 @@
+{
+  "best_global_step": 1708,
+  "best_metric": 4.332084655761719,
+  "best_model_checkpoint": null,
+  "epoch": 4.68384074941452,
+  "eval_steps": 500,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00234192037470726,
+      "grad_norm": 19.51460075378418,
+      "learning_rate": 0.0,
+      "loss": 10.4086,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.20932137966156,
+      "learning_rate": 8.52e-05,
+      "loss": 5.6615,
+      "step": 427
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 4.619469165802002,
+      "eval_runtime": 17.5001,
+      "eval_samples_per_second": 1285.705,
+      "eval_steps_per_second": 5.029,
+      "step": 427
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.7289506793022156,
+      "learning_rate": 7.83435582822086e-05,
+      "loss": 4.5174,
+      "step": 854
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 4.44211483001709,
+      "eval_runtime": 17.531,
+      "eval_samples_per_second": 1283.439,
+      "eval_steps_per_second": 5.02,
+      "step": 854
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.7140545845031738,
+      "learning_rate": 5.214723926380368e-05,
+      "loss": 4.4045,
+      "step": 1281
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 4.371854305267334,
+      "eval_runtime": 17.6718,
+      "eval_samples_per_second": 1273.212,
+      "eval_steps_per_second": 4.98,
+      "step": 1281
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.8016418218612671,
+      "learning_rate": 2.5950920245398774e-05,
+      "loss": 4.342,
+      "step": 1708
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 4.332084655761719,
+      "eval_runtime": 17.711,
+      "eval_samples_per_second": 1270.399,
+      "eval_steps_per_second": 4.969,
+      "step": 1708
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2135,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.3409060503552e+16,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baf1de3374fef5c10976a714bda99d8755482f90cd63f018682e2beee03c5178
+size 5969