Training in progress, step 2500, checkpoint

checkpoint-2500/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-2500/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-2500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50009dff000b32f6a8f2bda13c23fc5632354e17b678db09bffcd4e828f91717
+size 435544704

checkpoint-2500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82ddb30c10149166d39c081acaadf91fc8641c973f1cfd3ba1d50f5ffe119d67
+size 871183627

checkpoint-2500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ebe2032584cf805663ea2e8f10a38f5c431cd9ef3a229f2cb3eccdd54db159e
+size 14645

checkpoint-2500/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:861ce13e6ca091acee9a68ebfc5ca38479baf4b537c37b3949f071f77b81e9f0
+size 1383

checkpoint-2500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64c18a5545cf4e21a4422263bfc3007c9e2394c3dc59701db7dccff41ed54c63
+size 1465

checkpoint-2500/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-2500/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-2500/trainer_state.json

@@ -0,0 +1,131 @@
+{
+  "best_global_step": 2352,
+  "best_metric": 5.250909805297852,
+  "best_model_checkpoint": null,
+  "epoch": 6.377551020408164,
+  "eval_steps": 500,
+  "global_step": 2500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.002551020408163265,
+      "grad_norm": 15.423666000366211,
+      "learning_rate": 0.0,
+      "loss": 10.3767,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.1298359632492065,
+      "learning_rate": 7.82e-05,
+      "loss": 6.8906,
+      "step": 392
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 5.937362194061279,
+      "eval_runtime": 19.3187,
+      "eval_samples_per_second": 1305.007,
+      "eval_steps_per_second": 5.125,
+      "step": 392
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.8016104698181152,
+      "learning_rate": 9.613387978142077e-05,
+      "loss": 5.6886,
+      "step": 784
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 5.585238933563232,
+      "eval_runtime": 19.328,
+      "eval_samples_per_second": 1304.377,
+      "eval_steps_per_second": 5.122,
+      "step": 784
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.7857697010040283,
+      "learning_rate": 9.077868852459017e-05,
+      "loss": 5.4588,
+      "step": 1176
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 5.453728675842285,
+      "eval_runtime": 19.3626,
+      "eval_samples_per_second": 1302.043,
+      "eval_steps_per_second": 5.113,
+      "step": 1176
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.7446259260177612,
+      "learning_rate": 8.542349726775956e-05,
+      "loss": 5.3304,
+      "step": 1568
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 5.365298748016357,
+      "eval_runtime": 19.4192,
+      "eval_samples_per_second": 1298.248,
+      "eval_steps_per_second": 5.098,
+      "step": 1568
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.7833443284034729,
+      "learning_rate": 8.006830601092896e-05,
+      "loss": 5.2311,
+      "step": 1960
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 5.299525260925293,
+      "eval_runtime": 19.463,
+      "eval_samples_per_second": 1295.327,
+      "eval_steps_per_second": 5.087,
+      "step": 1960
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.8031137585639954,
+      "learning_rate": 7.471311475409837e-05,
+      "loss": 5.1454,
+      "step": 2352
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 5.250909805297852,
+      "eval_runtime": 19.6037,
+      "eval_samples_per_second": 1286.031,
+      "eval_steps_per_second": 5.05,
+      "step": 2352
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 7840,
+  "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": 4.1771842633728e+16,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95c7b5d187be0ad88516959ecbdbb33b361a3c89c931f1695e421a67d02fab8b
+size 5905