Training in progress, step 5000, checkpoint

checkpoint-5000/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-5000/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-5000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:860a77a5c0f54bd61620cfd949e4fa6692af5a58e63b46d8096d66f871aed033
+size 435544704

checkpoint-5000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:589658e9d991cb7c9985f4e5f8b2d164167772034a258e846087eca54c96203e
+size 871183627

checkpoint-5000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9525128fe426413b5a57324ee23f5f403b09fc9c5e695b320dbc607718b18b18
+size 14709

checkpoint-5000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82ad8990572ad11a824b7db276c8af49c179ca7e7724b4e6906cd0ae480a80a8
+size 1383

checkpoint-5000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5ff923f8206367eac93b66a45c8a421164d9265393b38c6653faad4e66f12ab
+size 1465

checkpoint-5000/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-5000/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-5000/trainer_state.json

@@ -0,0 +1,221 @@
+{
+  "best_global_step": 4800,
+  "best_metric": 5.383272171020508,
+  "best_model_checkpoint": null,
+  "epoch": 12.5,
+  "eval_steps": 500,
+  "global_step": 5000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0025,
+      "grad_norm": 16.100624084472656,
+      "learning_rate": 0.0,
+      "loss": 10.3279,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.404994249343872,
+      "learning_rate": 7.98e-05,
+      "loss": 7.0427,
+      "step": 400
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 6.198990345001221,
+      "eval_runtime": 42.1632,
+      "eval_samples_per_second": 609.275,
+      "eval_steps_per_second": 2.395,
+      "step": 400
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.2766317129135132,
+      "learning_rate": 9.600267379679145e-05,
+      "loss": 5.9607,
+      "step": 800
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 5.85300350189209,
+      "eval_runtime": 44.0748,
+      "eval_samples_per_second": 582.85,
+      "eval_steps_per_second": 2.292,
+      "step": 800
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.36733078956604,
+      "learning_rate": 9.065508021390375e-05,
+      "loss": 5.7343,
+      "step": 1200
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 5.715977668762207,
+      "eval_runtime": 44.0451,
+      "eval_samples_per_second": 583.243,
+      "eval_steps_per_second": 2.293,
+      "step": 1200
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.3367751836776733,
+      "learning_rate": 8.530748663101604e-05,
+      "loss": 5.6009,
+      "step": 1600
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 5.622774600982666,
+      "eval_runtime": 43.8815,
+      "eval_samples_per_second": 585.417,
+      "eval_steps_per_second": 2.302,
+      "step": 1600
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.3959336280822754,
+      "learning_rate": 7.995989304812834e-05,
+      "loss": 5.4929,
+      "step": 2000
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 5.5484700202941895,
+      "eval_runtime": 43.9851,
+      "eval_samples_per_second": 584.039,
+      "eval_steps_per_second": 2.296,
+      "step": 2000
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 1.500172734260559,
+      "learning_rate": 7.461229946524065e-05,
+      "loss": 5.3999,
+      "step": 2400
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 5.494987964630127,
+      "eval_runtime": 44.1149,
+      "eval_samples_per_second": 582.32,
+      "eval_steps_per_second": 2.289,
+      "step": 2400
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 1.5156828165054321,
+      "learning_rate": 6.926470588235294e-05,
+      "loss": 5.3184,
+      "step": 2800
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 5.4551777839660645,
+      "eval_runtime": 44.0519,
+      "eval_samples_per_second": 583.153,
+      "eval_steps_per_second": 2.293,
+      "step": 2800
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 1.7039804458618164,
+      "learning_rate": 6.391711229946524e-05,
+      "loss": 5.2448,
+      "step": 3200
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 5.4279961585998535,
+      "eval_runtime": 43.9751,
+      "eval_samples_per_second": 584.172,
+      "eval_steps_per_second": 2.297,
+      "step": 3200
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 1.7658451795578003,
+      "learning_rate": 5.8569518716577545e-05,
+      "loss": 5.1772,
+      "step": 3600
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 5.405717372894287,
+      "eval_runtime": 43.8709,
+      "eval_samples_per_second": 585.559,
+      "eval_steps_per_second": 2.302,
+      "step": 3600
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 1.9227123260498047,
+      "learning_rate": 5.322192513368984e-05,
+      "loss": 5.1132,
+      "step": 4000
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 5.394469738006592,
+      "eval_runtime": 44.0522,
+      "eval_samples_per_second": 583.149,
+      "eval_steps_per_second": 2.293,
+      "step": 4000
+    },
+    {
+      "epoch": 11.0,
+      "grad_norm": 2.014274835586548,
+      "learning_rate": 4.787433155080214e-05,
+      "loss": 5.0533,
+      "step": 4400
+    },
+    {
+      "epoch": 11.0,
+      "eval_loss": 5.386741638183594,
+      "eval_runtime": 43.9434,
+      "eval_samples_per_second": 584.593,
+      "eval_steps_per_second": 2.298,
+      "step": 4400
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 2.2169082164764404,
+      "learning_rate": 4.2526737967914444e-05,
+      "loss": 4.9969,
+      "step": 4800
+    },
+    {
+      "epoch": 12.0,
+      "eval_loss": 5.383272171020508,
+      "eval_runtime": 42.2904,
+      "eval_samples_per_second": 607.443,
+      "eval_steps_per_second": 2.388,
+      "step": 4800
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 8000,
+  "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": 8.3446484631552e+16,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-5000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e93e523a2c8dd3667d572b78883a2f62cc5aa37a91740c907d9e65d0f1ca2ef
+size 5905