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 sha256:7714a68ff834aa1934eb0f9285406cf1ba02db8487f1ad6e977f6cd2bab275b5
+size 435544704

checkpoint-5000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a0f8675fc828aafc9c8aed3757a1c58a6e48ef42f9edf685e43b22cd8e359f9
+size 871183627

checkpoint-5000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afc84bd23a789ac2c71baad6f82bd57a625b46c3f78f57d38b1f877060489d1a
+size 14645

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 sha256:78196df5851e7bb4911991ab85895a027930bef9fe6387d0ef6bb787245f2139
+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": 4788,
+  "best_metric": 5.558596611022949,
+  "best_model_checkpoint": null,
+  "epoch": 12.531328320802006,
+  "eval_steps": 500,
+  "global_step": 5000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.002506265664160401,
+      "grad_norm": 15.9864501953125,
+      "learning_rate": 0.0,
+      "loss": 10.417,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.8621832728385925,
+      "learning_rate": 7.960000000000001e-05,
+      "loss": 7.2645,
+      "step": 399
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 6.560304641723633,
+      "eval_runtime": 19.6689,
+      "eval_samples_per_second": 1301.09,
+      "eval_steps_per_second": 5.084,
+      "step": 399
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.8654030561447144,
+      "learning_rate": 9.601876675603218e-05,
+      "loss": 6.3052,
+      "step": 798
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 6.197527885437012,
+      "eval_runtime": 19.7032,
+      "eval_samples_per_second": 1298.827,
+      "eval_steps_per_second": 5.075,
+      "step": 798
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.8320090174674988,
+      "learning_rate": 9.067024128686328e-05,
+      "loss": 6.0403,
+      "step": 1197
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 6.017029762268066,
+      "eval_runtime": 19.6629,
+      "eval_samples_per_second": 1301.488,
+      "eval_steps_per_second": 5.086,
+      "step": 1197
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.9439840316772461,
+      "learning_rate": 8.532171581769438e-05,
+      "loss": 5.871,
+      "step": 1596
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 5.894550323486328,
+      "eval_runtime": 19.6913,
+      "eval_samples_per_second": 1299.609,
+      "eval_steps_per_second": 5.078,
+      "step": 1596
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.9222375154495239,
+      "learning_rate": 7.997319034852548e-05,
+      "loss": 5.7369,
+      "step": 1995
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 5.80098819732666,
+      "eval_runtime": 19.5829,
+      "eval_samples_per_second": 1306.806,
+      "eval_steps_per_second": 5.107,
+      "step": 1995
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.9949414730072021,
+      "learning_rate": 7.462466487935658e-05,
+      "loss": 5.6219,
+      "step": 2394
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 5.727022647857666,
+      "eval_runtime": 19.8404,
+      "eval_samples_per_second": 1289.845,
+      "eval_steps_per_second": 5.04,
+      "step": 2394
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 1.129814863204956,
+      "learning_rate": 6.927613941018766e-05,
+      "loss": 5.5208,
+      "step": 2793
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 5.671111583709717,
+      "eval_runtime": 19.6842,
+      "eval_samples_per_second": 1300.077,
+      "eval_steps_per_second": 5.08,
+      "step": 2793
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 1.1452852487564087,
+      "learning_rate": 6.392761394101878e-05,
+      "loss": 5.4309,
+      "step": 3192
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 5.631607532501221,
+      "eval_runtime": 19.587,
+      "eval_samples_per_second": 1306.528,
+      "eval_steps_per_second": 5.105,
+      "step": 3192
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 1.2302745580673218,
+      "learning_rate": 5.8579088471849864e-05,
+      "loss": 5.3491,
+      "step": 3591
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 5.599754333496094,
+      "eval_runtime": 19.5773,
+      "eval_samples_per_second": 1307.18,
+      "eval_steps_per_second": 5.108,
+      "step": 3591
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 1.3123430013656616,
+      "learning_rate": 5.3230563002680965e-05,
+      "loss": 5.273,
+      "step": 3990
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 5.580637454986572,
+      "eval_runtime": 19.6013,
+      "eval_samples_per_second": 1305.576,
+      "eval_steps_per_second": 5.102,
+      "step": 3990
+    },
+    {
+      "epoch": 11.0,
+      "grad_norm": 1.3928662538528442,
+      "learning_rate": 4.7882037533512065e-05,
+      "loss": 5.2025,
+      "step": 4389
+    },
+    {
+      "epoch": 11.0,
+      "eval_loss": 5.565992832183838,
+      "eval_runtime": 19.5753,
+      "eval_samples_per_second": 1307.309,
+      "eval_steps_per_second": 5.108,
+      "step": 4389
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 1.4923430681228638,
+      "learning_rate": 4.2533512064343165e-05,
+      "loss": 5.1371,
+      "step": 4788
+    },
+    {
+      "epoch": 12.0,
+      "eval_loss": 5.558596611022949,
+      "eval_runtime": 19.7434,
+      "eval_samples_per_second": 1296.181,
+      "eval_steps_per_second": 5.065,
+      "step": 4788
+    }
+  ],
+  "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": 8.3487246188544e+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 sha256:2ec9dad28d1f89f1f744465a1524080afbee7ab1c9bf9851246ed7f5c82dc55d
+size 5905