Training in progress, step 5500, checkpoint

checkpoint-5500/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-5500/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-5500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee871f8229e3c42fe615829e8adea3eae8066a7e4a3e9ca2c093eff3b8029833
+size 435544704

checkpoint-5500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9b5ff02bbb970822d84b31ec2e107aceddf1849e8c0953ee0c427b8c5c98bdc
+size 871183627

checkpoint-5500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4efda7796ce07ab229532419b65fb0260548ca11d0611b3f458b6be7390c11eb
+size 14709

checkpoint-5500/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bb8c4f79563cb7c9027a7d8be443142caa0e3f4a88491ec812af28bc90af134
+size 1383

checkpoint-5500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0595d6a578d6adb79043bc02b79f41222e29c501a0801815aebf3ed7da9f6b2
+size 1465

checkpoint-5500/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-5500/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-5500/trainer_state.json

@@ -0,0 +1,236 @@
+{
+  "best_global_step": 5187,
+  "best_metric": 5.991211414337158,
+  "best_model_checkpoint": null,
+  "epoch": 13.784461152882205,
+  "eval_steps": 500,
+  "global_step": 5500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.002506265664160401,
+      "grad_norm": 15.975584983825684,
+      "learning_rate": 0.0,
+      "loss": 10.3232,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.5802501440048218,
+      "learning_rate": 7.960000000000001e-05,
+      "loss": 7.3315,
+      "step": 399
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 6.782732009887695,
+      "eval_runtime": 20.1847,
+      "eval_samples_per_second": 1266.7,
+      "eval_steps_per_second": 4.954,
+      "step": 399
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.6263211965560913,
+      "learning_rate": 9.601876675603218e-05,
+      "loss": 6.5649,
+      "step": 798
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 6.505067348480225,
+      "eval_runtime": 20.2041,
+      "eval_samples_per_second": 1265.484,
+      "eval_steps_per_second": 4.949,
+      "step": 798
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.712126612663269,
+      "learning_rate": 9.067024128686328e-05,
+      "loss": 6.3596,
+      "step": 1197
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 6.374659061431885,
+      "eval_runtime": 20.1506,
+      "eval_samples_per_second": 1268.845,
+      "eval_steps_per_second": 4.963,
+      "step": 1197
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.8251084089279175,
+      "learning_rate": 8.532171581769438e-05,
+      "loss": 6.2374,
+      "step": 1596
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 6.283264636993408,
+      "eval_runtime": 20.2013,
+      "eval_samples_per_second": 1265.66,
+      "eval_steps_per_second": 4.95,
+      "step": 1596
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.9603049755096436,
+      "learning_rate": 7.997319034852548e-05,
+      "loss": 6.1394,
+      "step": 1995
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 6.215089321136475,
+      "eval_runtime": 20.1986,
+      "eval_samples_per_second": 1265.827,
+      "eval_steps_per_second": 4.951,
+      "step": 1995
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 2.2172093391418457,
+      "learning_rate": 7.462466487935658e-05,
+      "loss": 6.0523,
+      "step": 2394
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 6.1546783447265625,
+      "eval_runtime": 20.2273,
+      "eval_samples_per_second": 1264.033,
+      "eval_steps_per_second": 4.944,
+      "step": 2394
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 2.386784076690674,
+      "learning_rate": 6.927613941018766e-05,
+      "loss": 5.9717,
+      "step": 2793
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 6.105106353759766,
+      "eval_runtime": 20.1964,
+      "eval_samples_per_second": 1265.968,
+      "eval_steps_per_second": 4.951,
+      "step": 2793
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 2.4912607669830322,
+      "learning_rate": 6.392761394101878e-05,
+      "loss": 5.8959,
+      "step": 3192
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 6.066310405731201,
+      "eval_runtime": 20.247,
+      "eval_samples_per_second": 1262.807,
+      "eval_steps_per_second": 4.939,
+      "step": 3192
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 2.7412707805633545,
+      "learning_rate": 5.8579088471849864e-05,
+      "loss": 5.8244,
+      "step": 3591
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 6.037230968475342,
+      "eval_runtime": 20.1932,
+      "eval_samples_per_second": 1266.167,
+      "eval_steps_per_second": 4.952,
+      "step": 3591
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 2.8698410987854004,
+      "learning_rate": 5.3230563002680965e-05,
+      "loss": 5.7569,
+      "step": 3990
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 6.01580286026001,
+      "eval_runtime": 20.2867,
+      "eval_samples_per_second": 1260.331,
+      "eval_steps_per_second": 4.929,
+      "step": 3990
+    },
+    {
+      "epoch": 11.0,
+      "grad_norm": 3.129441976547241,
+      "learning_rate": 4.7882037533512065e-05,
+      "loss": 5.6931,
+      "step": 4389
+    },
+    {
+      "epoch": 11.0,
+      "eval_loss": 6.006232261657715,
+      "eval_runtime": 20.2433,
+      "eval_samples_per_second": 1263.034,
+      "eval_steps_per_second": 4.94,
+      "step": 4389
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 3.506577491760254,
+      "learning_rate": 4.2533512064343165e-05,
+      "loss": 5.6331,
+      "step": 4788
+    },
+    {
+      "epoch": 12.0,
+      "eval_loss": 5.995199203491211,
+      "eval_runtime": 20.2546,
+      "eval_samples_per_second": 1262.328,
+      "eval_steps_per_second": 4.937,
+      "step": 4788
+    },
+    {
+      "epoch": 13.0,
+      "grad_norm": 3.698240280151367,
+      "learning_rate": 3.7184986595174266e-05,
+      "loss": 5.5764,
+      "step": 5187
+    },
+    {
+      "epoch": 13.0,
+      "eval_loss": 5.991211414337158,
+      "eval_runtime": 20.2016,
+      "eval_samples_per_second": 1265.641,
+      "eval_steps_per_second": 4.95,
+      "step": 5187
+    }
+  ],
+  "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": 9.1767590682624e+16,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-5500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac4d63aaf716a2b718a7169b48d63dcbfe3277f2ba392e40697191d51fad5cc6
+size 5969