Training in progress, step 3500, checkpoint

checkpoint-3500/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-3500/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-3500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19915cdcc138dd3809859375509173b624f2e93925305cf001bf8d45dc9dec3d
+size 435544704

checkpoint-3500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2e780d519e8130302769f2c4b75bbeb9f47a418c6e19f2add6f4d1f55012d7a
+size 871183627

checkpoint-3500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9839d6098bd5b6f92b39e6cf2166c815af4bbea936e9e7a16a9aced5b206e3d6
+size 14709

checkpoint-3500/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac1b9358ab1cb9acff90f4d1d692ac08bbdb1986a66544aed9f6fe9b801b17b3
+size 1383

checkpoint-3500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb32fbd19fcf44c9ad6a7a6d8fcc7198ba666c7b0d67c5fd3fb1d1f1f9b92ef5
+size 1465

checkpoint-3500/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-3500/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-3500/trainer_state.json

@@ -0,0 +1,161 @@
+{
+  "best_global_step": 3376,
+  "best_metric": 4.544655799865723,
+  "best_model_checkpoint": null,
+  "epoch": 8.293838862559241,
+  "eval_steps": 500,
+  "global_step": 3500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.002369668246445498,
+      "grad_norm": 20.529037475585938,
+      "learning_rate": 0.0,
+      "loss": 10.3272,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.7308573126792908,
+      "learning_rate": 8.42e-05,
+      "loss": 5.8069,
+      "step": 422
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 4.889161109924316,
+      "eval_runtime": 24.7918,
+      "eval_samples_per_second": 1110.931,
+      "eval_steps_per_second": 4.356,
+      "step": 422
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.6186949610710144,
+      "learning_rate": 9.566919191919192e-05,
+      "loss": 4.7607,
+      "step": 844
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 4.739172458648682,
+      "eval_runtime": 25.1721,
+      "eval_samples_per_second": 1094.147,
+      "eval_steps_per_second": 4.29,
+      "step": 844
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.48522624373435974,
+      "learning_rate": 9.03409090909091e-05,
+      "loss": 4.655,
+      "step": 1266
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 4.66502571105957,
+      "eval_runtime": 24.8803,
+      "eval_samples_per_second": 1106.979,
+      "eval_steps_per_second": 4.341,
+      "step": 1266
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.5602008700370789,
+      "learning_rate": 8.501262626262628e-05,
+      "loss": 4.59,
+      "step": 1688
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 4.622807502746582,
+      "eval_runtime": 25.1017,
+      "eval_samples_per_second": 1097.217,
+      "eval_steps_per_second": 4.302,
+      "step": 1688
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.48087647557258606,
+      "learning_rate": 7.968434343434343e-05,
+      "loss": 4.5422,
+      "step": 2110
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 4.595207214355469,
+      "eval_runtime": 25.2481,
+      "eval_samples_per_second": 1090.855,
+      "eval_steps_per_second": 4.278,
+      "step": 2110
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.5272459983825684,
+      "learning_rate": 7.435606060606061e-05,
+      "loss": 4.5019,
+      "step": 2532
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 4.570671081542969,
+      "eval_runtime": 24.8077,
+      "eval_samples_per_second": 1110.221,
+      "eval_steps_per_second": 4.353,
+      "step": 2532
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.5141113996505737,
+      "learning_rate": 6.902777777777779e-05,
+      "loss": 4.4653,
+      "step": 2954
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 4.554932117462158,
+      "eval_runtime": 25.0344,
+      "eval_samples_per_second": 1100.168,
+      "eval_steps_per_second": 4.314,
+      "step": 2954
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.5404757857322693,
+      "learning_rate": 6.369949494949495e-05,
+      "loss": 4.4302,
+      "step": 3376
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 4.544655799865723,
+      "eval_runtime": 25.1458,
+      "eval_samples_per_second": 1095.294,
+      "eval_steps_per_second": 4.295,
+      "step": 3376
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 8440,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "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": 5.852418932736e+16,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-3500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba4b7323fccf801a5ad3c46619165967074d83bf45834933a136db608217d63c
+size 5969