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:a3f5beb275cbcf767ea957abe51c5605f423be4188495a499684ccd9ffd27e15
+size 435544704

checkpoint-2500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4be20d0878827aaa9999a52029c3626266ab76915b33bf6563c358ffa7073725
+size 871183627

checkpoint-2500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:567333e0e5b0cbd4dff6aa1ef81d1b39805d625b39d25f3c7b3eac52a8a73a74
+size 14645

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 sha256:1916907542469ad8dac575e1196900e2c1892c60bc35375a7e0c96f35bc67fb4
+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 +1,131 @@
+{
+  "best_global_step": 2394,
+  "best_metric": 5.728259086608887,
+  "best_model_checkpoint": null,
+  "epoch": 6.265664160401003,
+  "eval_steps": 500,
+  "global_step": 2500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.002506265664160401,
+      "grad_norm": 15.486847877502441,
+      "learning_rate": 0.0,
+      "loss": 10.3817,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.988777756690979,
+      "learning_rate": 7.960000000000001e-05,
+      "loss": 7.2659,
+      "step": 399
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 6.563127040863037,
+      "eval_runtime": 19.6799,
+      "eval_samples_per_second": 1300.365,
+      "eval_steps_per_second": 5.081,
+      "step": 399
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.8962027430534363,
+      "learning_rate": 9.601876675603218e-05,
+      "loss": 6.3067,
+      "step": 798
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 6.204437255859375,
+      "eval_runtime": 19.5845,
+      "eval_samples_per_second": 1306.694,
+      "eval_steps_per_second": 5.106,
+      "step": 798
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.8679091334342957,
+      "learning_rate": 9.067024128686328e-05,
+      "loss": 6.0406,
+      "step": 1197
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 6.018397808074951,
+      "eval_runtime": 19.6084,
+      "eval_samples_per_second": 1305.103,
+      "eval_steps_per_second": 5.1,
+      "step": 1197
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.9358043074607849,
+      "learning_rate": 8.532171581769438e-05,
+      "loss": 5.8724,
+      "step": 1596
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 5.89630651473999,
+      "eval_runtime": 19.7935,
+      "eval_samples_per_second": 1292.902,
+      "eval_steps_per_second": 5.052,
+      "step": 1596
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.971953809261322,
+      "learning_rate": 7.997319034852548e-05,
+      "loss": 5.7384,
+      "step": 1995
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 5.800810813903809,
+      "eval_runtime": 19.6145,
+      "eval_samples_per_second": 1304.696,
+      "eval_steps_per_second": 5.098,
+      "step": 1995
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 1.0337553024291992,
+      "learning_rate": 7.462466487935658e-05,
+      "loss": 5.6236,
+      "step": 2394
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 5.728259086608887,
+      "eval_runtime": 19.8046,
+      "eval_samples_per_second": 1292.172,
+      "eval_steps_per_second": 5.049,
+      "step": 2394
+    }
+  ],
+  "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": 4.1743623094272e+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:ed5469620139c1b9e18cc193389d8694ad90a34f9c1417f0546e2dad424a3d38
+size 5905