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 sha256:0190b3f201b5d4bf5d1121fe982381dea740ea5750302d1d54087549a74981ba
+size 435544704

checkpoint-3500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d503d5ad623bc9a3bc6c71c999b185ccff9918a2ddb4cce7ff1728a05739cbab
+size 871183627

checkpoint-3500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d0f4bc1c597c7c15e47f9b4afcedd64865e5024e604d93c2a624a176fd97ede
+size 14645

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 sha256:5a288da85b69343231049c60639ecaacafce98969e38a86e086b07385ebfe271
+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 +1,146 @@
+{
+  "best_global_step": 3465,
+  "best_metric": 3.092864751815796,
+  "best_model_checkpoint": null,
+  "epoch": 7.070707070707071,
+  "eval_steps": 500,
+  "global_step": 3500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00202020202020202,
+      "grad_norm": 29.864723205566406,
+      "learning_rate": 0.0,
+      "loss": 10.4445,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.278876543045044,
+      "learning_rate": 9.88e-05,
+      "loss": 4.8246,
+      "step": 495
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 3.7829103469848633,
+      "eval_runtime": 19.668,
+      "eval_samples_per_second": 1616.332,
+      "eval_steps_per_second": 6.356,
+      "step": 495
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.0388227701187134,
+      "learning_rate": 9.478678038379531e-05,
+      "loss": 3.5358,
+      "step": 990
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 3.4372856616973877,
+      "eval_runtime": 19.5671,
+      "eval_samples_per_second": 1624.666,
+      "eval_steps_per_second": 6.388,
+      "step": 990
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.9951871037483215,
+      "learning_rate": 8.950959488272922e-05,
+      "loss": 3.2822,
+      "step": 1485
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 3.2929306030273438,
+      "eval_runtime": 19.6808,
+      "eval_samples_per_second": 1615.277,
+      "eval_steps_per_second": 6.351,
+      "step": 1485
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.0897934436798096,
+      "learning_rate": 8.42324093816631e-05,
+      "loss": 3.1379,
+      "step": 1980
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 3.211028575897217,
+      "eval_runtime": 19.92,
+      "eval_samples_per_second": 1595.88,
+      "eval_steps_per_second": 6.275,
+      "step": 1980
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.1176131963729858,
+      "learning_rate": 7.895522388059702e-05,
+      "loss": 3.0361,
+      "step": 2475
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 3.154623031616211,
+      "eval_runtime": 19.6905,
+      "eval_samples_per_second": 1614.486,
+      "eval_steps_per_second": 6.348,
+      "step": 2475
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 1.1129180192947388,
+      "learning_rate": 7.367803837953093e-05,
+      "loss": 2.9554,
+      "step": 2970
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 3.116886854171753,
+      "eval_runtime": 19.7127,
+      "eval_samples_per_second": 1612.665,
+      "eval_steps_per_second": 6.341,
+      "step": 2970
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 1.1529704332351685,
+      "learning_rate": 6.840085287846483e-05,
+      "loss": 2.8872,
+      "step": 3465
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 3.092864751815796,
+      "eval_runtime": 19.8571,
+      "eval_samples_per_second": 1600.942,
+      "eval_steps_per_second": 6.295,
+      "step": 3465
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 9900,
+  "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": 5.8462197792768e+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:e3ba2b587986deaa450c61da6054c5361c47fea7494b7c4371ba7068b7679ad3
+size 5905