Training in progress, step 2000, checkpoint

checkpoint-2000/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-2000/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-2000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09160a88284baac33bd8e228ce7a4cdd604d68e54f8f9bc8ba0bf664ee72c5cc
+size 435544704

checkpoint-2000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c059951a4244b4d30a710e09c1bcfea9ba58a1a0fc9b8ead4a7f0bf96f3e0305
+size 871183627

checkpoint-2000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1679b05676279e653d045b4e018b0480fc524430b3a0ba76d5c05c14ef9e318
+size 14645

checkpoint-2000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4aa03f6e0cd07cf67ce1fbe3101d545f5771ef9148b9debf02b11cf6948da5c
+size 1383

checkpoint-2000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79ada9d37a38356af9c7a8aba0d1a81c174e69d01d365d71b038fb5e4bb625ef
+size 1465

checkpoint-2000/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-2000/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-2000/trainer_state.json

@@ -0,0 +1,101 @@
+{
+  "best_global_step": 1984,
+  "best_metric": 2.807156801223755,
+  "best_model_checkpoint": null,
+  "epoch": 4.032258064516129,
+  "eval_steps": 500,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0020161290322580645,
+      "grad_norm": 29.116209030151367,
+      "learning_rate": 0.0,
+      "loss": 10.3845,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.1071062088012695,
+      "learning_rate": 9.900000000000001e-05,
+      "loss": 4.4941,
+      "step": 496
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 3.292287588119507,
+      "eval_runtime": 19.6975,
+      "eval_samples_per_second": 1617.054,
+      "eval_steps_per_second": 6.346,
+      "step": 496
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.7607663869857788,
+      "learning_rate": 9.477659574468086e-05,
+      "loss": 3.0413,
+      "step": 992
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 2.9782464504241943,
+      "eval_runtime": 19.6472,
+      "eval_samples_per_second": 1621.2,
+      "eval_steps_per_second": 6.362,
+      "step": 992
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.7289094924926758,
+      "learning_rate": 8.950000000000001e-05,
+      "loss": 2.8102,
+      "step": 1488
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 2.868624210357666,
+      "eval_runtime": 19.7132,
+      "eval_samples_per_second": 1615.769,
+      "eval_steps_per_second": 6.341,
+      "step": 1488
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.7236714959144592,
+      "learning_rate": 8.422340425531914e-05,
+      "loss": 2.6891,
+      "step": 1984
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 2.807156801223755,
+      "eval_runtime": 19.9586,
+      "eval_samples_per_second": 1595.9,
+      "eval_steps_per_second": 6.263,
+      "step": 1984
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 9920,
+  "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": 3.3426567069696e+16,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16787e1a691b66b74542c851d1e76d5c8f71c0bd9080cae1059f2207e6ddffe2
+size 5905