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:b27549de8b4465378d083e72648e4fa276595a121355620251d3b6dee210a9a3
+size 435544704

checkpoint-3500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:838d288ec43b31328ad6772c7cca735f53f34d5198d69865a605803924dfc5ff
+size 871183627

checkpoint-3500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6f53d813d98fb131fc03101f404ce9c8ee3d11bcee6afed4cc79c2dc821d3c9
+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 sha256:5a288da85b69343231049c60639ecaacafce98969e38a86e086b07385ebfe271
+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": 3.1518795490264893,
+  "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": 27.219696044921875,
+      "learning_rate": 0.0,
+      "loss": 10.3707,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.5280556678771973,
+      "learning_rate": 9.88e-05,
+      "loss": 4.8958,
+      "step": 495
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 3.9314539432525635,
+      "eval_runtime": 29.8878,
+      "eval_samples_per_second": 1062.842,
+      "eval_steps_per_second": 4.182,
+      "step": 495
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 3.212111234664917,
+      "learning_rate": 9.478678038379531e-05,
+      "loss": 3.6499,
+      "step": 990
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 3.539745330810547,
+      "eval_runtime": 29.254,
+      "eval_samples_per_second": 1085.869,
+      "eval_steps_per_second": 4.273,
+      "step": 990
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 3.3252358436584473,
+      "learning_rate": 8.950959488272922e-05,
+      "loss": 3.3793,
+      "step": 1485
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 3.379368305206299,
+      "eval_runtime": 30.2558,
+      "eval_samples_per_second": 1049.913,
+      "eval_steps_per_second": 4.131,
+      "step": 1485
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 3.02847957611084,
+      "learning_rate": 8.42324093816631e-05,
+      "loss": 3.2264,
+      "step": 1980
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 3.2874038219451904,
+      "eval_runtime": 30.0535,
+      "eval_samples_per_second": 1056.98,
+      "eval_steps_per_second": 4.159,
+      "step": 1980
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 3.101438045501709,
+      "learning_rate": 7.895522388059702e-05,
+      "loss": 3.1179,
+      "step": 2475
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 3.2294254302978516,
+      "eval_runtime": 27.6091,
+      "eval_samples_per_second": 1150.562,
+      "eval_steps_per_second": 4.527,
+      "step": 2475
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 3.4466798305511475,
+      "learning_rate": 7.367803837953093e-05,
+      "loss": 3.0343,
+      "step": 2970
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 3.183612585067749,
+      "eval_runtime": 29.4719,
+      "eval_samples_per_second": 1077.841,
+      "eval_steps_per_second": 4.241,
+      "step": 2970
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 3.7074270248413086,
+      "learning_rate": 6.840085287846483e-05,
+      "loss": 2.9631,
+      "step": 3465
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 3.1518795490264893,
+      "eval_runtime": 30.1176,
+      "eval_samples_per_second": 1054.732,
+      "eval_steps_per_second": 4.15,
+      "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": 5.8416928948224e+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:a94c5b5396046cc73aa40d54564c0b9f4e9ee0bc4bd0cd62dd2c6c9d69210b54
+size 5905