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 sha256:8717aa21b0740749a4e61786e986144b808551ae45a1f7bb92d83176fd8b0ba8
+size 435544704

checkpoint-2500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b764247e4608855750252cc5d7d61c75c6d4be5ca2d88be43ae2d0f48f897b5a
+size 871183627

checkpoint-2500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba8c150e992d14d57e2740dd3f5f25f008c4f78fc719c88d24f1edead239b6f1
+size 14709

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:bab6f407b96e4677ac49f44ee259ec721506750ffba9b8de6052b40026b06ea7
+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 +1,101 @@
+{
+  "best_global_step": 2012,
+  "best_metric": 3.18221378326416,
+  "best_model_checkpoint": null,
+  "epoch": 4.970178926441352,
+  "eval_steps": 500,
+  "global_step": 2500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0019880715705765406,
+      "grad_norm": 30.286874771118164,
+      "learning_rate": 0.0,
+      "loss": 10.4037,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.5649309158325195,
+      "learning_rate": 9.990049751243782e-05,
+      "loss": 4.5769,
+      "step": 503
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 3.519712209701538,
+      "eval_runtime": 20.0659,
+      "eval_samples_per_second": 1582.434,
+      "eval_steps_per_second": 6.229,
+      "step": 503
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 4.33253812789917,
+      "learning_rate": 7.487562189054727e-05,
+      "loss": 3.322,
+      "step": 1006
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 3.3002562522888184,
+      "eval_runtime": 19.9319,
+      "eval_samples_per_second": 1593.072,
+      "eval_steps_per_second": 6.271,
+      "step": 1006
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 4.395430564880371,
+      "learning_rate": 4.985074626865672e-05,
+      "loss": 3.1705,
+      "step": 1509
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 3.2237703800201416,
+      "eval_runtime": 20.0466,
+      "eval_samples_per_second": 1583.963,
+      "eval_steps_per_second": 6.235,
+      "step": 1509
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 4.895762920379639,
+      "learning_rate": 2.482587064676617e-05,
+      "loss": 3.0902,
+      "step": 2012
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 3.18221378326416,
+      "eval_runtime": 20.1796,
+      "eval_samples_per_second": 1573.517,
+      "eval_steps_per_second": 6.194,
+      "step": 2012
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2515,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "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": 4.1740879527936e+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:dbadbc9569720773994790c3cab01a01ad3d053aeceb5489a3f461ffef8d7cba
+size 5969