Training in progress, step 4500, checkpoint

checkpoint-4500/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-4500/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-4500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:218a05ddcacac11724717978929f4054305d4651e193fb66d63f35f483385aa2
+size 435544704

checkpoint-4500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00670f3cff3732d84603a32d87d658fccec3a5dba0dbb76146fd5401fb7a90a2
+size 871183627

checkpoint-4500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4512a96eba6ff64198cdca63c09370670a33ca095f26465c8ac0a7e1d86c1fe0
+size 14709

checkpoint-4500/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b62db0ba9861d9ab63380744e79a287faa461a1bf55700140a411fe1e976f1cd
+size 1383

checkpoint-4500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b727ccc25e771bfc79dc9100e4e7ccdb53ecae619843cfc270f9d32d893e558
+size 1465

checkpoint-4500/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-4500/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-4500/trainer_state.json

@@ -0,0 +1,206 @@
+{
+  "best_global_step": 4389,
+  "best_metric": 5.56897497177124,
+  "best_model_checkpoint": null,
+  "epoch": 11.278195488721805,
+  "eval_steps": 500,
+  "global_step": 4500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.002506265664160401,
+      "grad_norm": 16.11646270751953,
+      "learning_rate": 0.0,
+      "loss": 10.385,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.8892227411270142,
+      "learning_rate": 7.960000000000001e-05,
+      "loss": 7.2503,
+      "step": 399
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 6.564814567565918,
+      "eval_runtime": 15.8497,
+      "eval_samples_per_second": 1614.608,
+      "eval_steps_per_second": 6.309,
+      "step": 399
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.8747593760490417,
+      "learning_rate": 9.601876675603218e-05,
+      "loss": 6.3058,
+      "step": 798
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 6.198642730712891,
+      "eval_runtime": 15.845,
+      "eval_samples_per_second": 1615.087,
+      "eval_steps_per_second": 6.311,
+      "step": 798
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.8593358397483826,
+      "learning_rate": 9.067024128686328e-05,
+      "loss": 6.0421,
+      "step": 1197
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 6.022042274475098,
+      "eval_runtime": 15.9011,
+      "eval_samples_per_second": 1609.382,
+      "eval_steps_per_second": 6.289,
+      "step": 1197
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.9470396637916565,
+      "learning_rate": 8.532171581769438e-05,
+      "loss": 5.8743,
+      "step": 1596
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 5.898093223571777,
+      "eval_runtime": 15.8847,
+      "eval_samples_per_second": 1611.046,
+      "eval_steps_per_second": 6.295,
+      "step": 1596
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.9495080709457397,
+      "learning_rate": 7.997319034852548e-05,
+      "loss": 5.7397,
+      "step": 1995
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 5.80107307434082,
+      "eval_runtime": 15.8032,
+      "eval_samples_per_second": 1619.353,
+      "eval_steps_per_second": 6.328,
+      "step": 1995
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 1.0368378162384033,
+      "learning_rate": 7.462466487935658e-05,
+      "loss": 5.6244,
+      "step": 2394
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 5.727475166320801,
+      "eval_runtime": 15.9058,
+      "eval_samples_per_second": 1608.907,
+      "eval_steps_per_second": 6.287,
+      "step": 2394
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 1.073407769203186,
+      "learning_rate": 6.927613941018766e-05,
+      "loss": 5.5233,
+      "step": 2793
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 5.67384672164917,
+      "eval_runtime": 15.8859,
+      "eval_samples_per_second": 1610.926,
+      "eval_steps_per_second": 6.295,
+      "step": 2793
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 1.1990339756011963,
+      "learning_rate": 6.392761394101878e-05,
+      "loss": 5.4332,
+      "step": 3192
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 5.6314849853515625,
+      "eval_runtime": 15.8644,
+      "eval_samples_per_second": 1613.112,
+      "eval_steps_per_second": 6.303,
+      "step": 3192
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 1.2410649061203003,
+      "learning_rate": 5.8579088471849864e-05,
+      "loss": 5.3508,
+      "step": 3591
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 5.602941513061523,
+      "eval_runtime": 15.9435,
+      "eval_samples_per_second": 1605.103,
+      "eval_steps_per_second": 6.272,
+      "step": 3591
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 1.3589402437210083,
+      "learning_rate": 5.3230563002680965e-05,
+      "loss": 5.2752,
+      "step": 3990
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 5.583064556121826,
+      "eval_runtime": 15.922,
+      "eval_samples_per_second": 1607.277,
+      "eval_steps_per_second": 6.281,
+      "step": 3990
+    },
+    {
+      "epoch": 11.0,
+      "grad_norm": 1.4183598756790161,
+      "learning_rate": 4.7882037533512065e-05,
+      "loss": 5.2046,
+      "step": 4389
+    },
+    {
+      "epoch": 11.0,
+      "eval_loss": 5.56897497177124,
+      "eval_runtime": 15.8908,
+      "eval_samples_per_second": 1610.427,
+      "eval_steps_per_second": 6.293,
+      "step": 4389
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 7980,
+  "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": 7.5136418168832e+16,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-4500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d9cd5a50fb229d5a9f661ee1910cd9975b067204b4a207aaaffcbd1b30a2f59
+size 5905