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:e4cd4bc1654cb310c4410b04cb58f7840c05d4b4006574f26eda48148558e890
+size 435544704

checkpoint-2500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:956bc5fe1a38406599deaf0a521c397215b677b78f7cab33b55bf73bc165a523
+size 871183627

checkpoint-2500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46c9519376dd2c876178e0312d8f7836ca1f062727edf43cc58693d9d76ff57b
+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 sha256:91f945cb78ff52f90c8c4b3f28930f91bad65b4e68dda8b22a5358df897eb7e1
+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 +1,116 @@
+{
+  "best_global_step": 2480,
+  "best_metric": 2.76945161819458,
+  "best_model_checkpoint": null,
+  "epoch": 5.040322580645161,
+  "eval_steps": 500,
+  "global_step": 2500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0020161290322580645,
+      "grad_norm": 26.651273727416992,
+      "learning_rate": 0.0,
+      "loss": 10.3824,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.098850131034851,
+      "learning_rate": 9.900000000000001e-05,
+      "loss": 4.4925,
+      "step": 496
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 3.2907111644744873,
+      "eval_runtime": 19.696,
+      "eval_samples_per_second": 1617.185,
+      "eval_steps_per_second": 6.346,
+      "step": 496
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.778118908405304,
+      "learning_rate": 9.477659574468086e-05,
+      "loss": 3.0409,
+      "step": 992
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 2.979689836502075,
+      "eval_runtime": 19.6744,
+      "eval_samples_per_second": 1618.957,
+      "eval_steps_per_second": 6.353,
+      "step": 992
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.7490440607070923,
+      "learning_rate": 8.950000000000001e-05,
+      "loss": 2.8112,
+      "step": 1488
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 2.8685014247894287,
+      "eval_runtime": 19.6807,
+      "eval_samples_per_second": 1618.438,
+      "eval_steps_per_second": 6.351,
+      "step": 1488
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.7581645250320435,
+      "learning_rate": 8.422340425531914e-05,
+      "loss": 2.6901,
+      "step": 1984
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 2.8072190284729004,
+      "eval_runtime": 19.9442,
+      "eval_samples_per_second": 1597.056,
+      "eval_steps_per_second": 6.267,
+      "step": 1984
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.7085155844688416,
+      "learning_rate": 7.894680851063831e-05,
+      "loss": 2.6066,
+      "step": 2480
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 2.76945161819458,
+      "eval_runtime": 19.6801,
+      "eval_samples_per_second": 1618.484,
+      "eval_steps_per_second": 6.352,
+      "step": 2480
+    }
+  ],
+  "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": 4.178320883712e+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 sha256:80a28f6964e57a6b6c304cd870efb8784265c8b1f5db42d483504309ea764a3c
+size 5905