Training in progress, step 2000, checkpoint

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87ea4ace6a540586d0d8fc8bf83f7e73daad02efd1f7cd1a6c188b463f0c6259
+size 499730128

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfd57e75500fd17d26ecdf881bc717d13a68ea98a0a6fd85deb5052ef3a991b5
+size 812034507

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d920d35377b6218b0a182ca529dc7f210a3398080e4578011b7878234683794
+size 14645

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e05547d8b4c2d503eaa441cb32a0d85a52189a237174a52b21fcd639756dcd0
+size 1465

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "backend": "tokenizers",
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,192 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.04,
+  "eval_steps": 1000,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.002,
+      "grad_norm": 1.0905472040176392,
+      "learning_rate": 0.0007920000000000001,
+      "loss": 7.247091674804688,
+      "step": 100
+    },
+    {
+      "epoch": 0.004,
+      "grad_norm": 2.1956381797790527,
+      "learning_rate": 0.001592,
+      "loss": 5.962919311523438,
+      "step": 200
+    },
+    {
+      "epoch": 0.006,
+      "grad_norm": 0.7685134410858154,
+      "learning_rate": 0.002392,
+      "loss": 5.536254272460938,
+      "step": 300
+    },
+    {
+      "epoch": 0.008,
+      "grad_norm": 0.6038330793380737,
+      "learning_rate": 0.003192,
+      "loss": 5.27086181640625,
+      "step": 400
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 0.38015660643577576,
+      "learning_rate": 0.003992,
+      "loss": 5.034593505859375,
+      "step": 500
+    },
+    {
+      "epoch": 0.012,
+      "grad_norm": 0.25242117047309875,
+      "learning_rate": 0.004792,
+      "loss": 4.90749267578125,
+      "step": 600
+    },
+    {
+      "epoch": 0.014,
+      "grad_norm": 0.2624945342540741,
+      "learning_rate": 0.005592000000000001,
+      "loss": 4.80042236328125,
+      "step": 700
+    },
+    {
+      "epoch": 0.016,
+      "grad_norm": 0.17131584882736206,
+      "learning_rate": 0.006392,
+      "loss": 4.716185607910156,
+      "step": 800
+    },
+    {
+      "epoch": 0.018,
+      "grad_norm": 0.2284715175628662,
+      "learning_rate": 0.007192,
+      "loss": 4.674341430664063,
+      "step": 900
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.24492475390434265,
+      "learning_rate": 0.007992,
+      "loss": 4.623594665527344,
+      "step": 1000
+    },
+    {
+      "epoch": 0.02,
+      "eval_accuracy": 0.24955772994129158,
+      "eval_loss": 4.598090648651123,
+      "eval_runtime": 4.6622,
+      "eval_samples_per_second": 214.491,
+      "eval_steps_per_second": 1.716,
+      "step": 1000
+    },
+    {
+      "epoch": 0.022,
+      "grad_norm": 0.16292935609817505,
+      "learning_rate": 0.008792,
+      "loss": 4.553927307128906,
+      "step": 1100
+    },
+    {
+      "epoch": 0.024,
+      "grad_norm": 0.15358929336071014,
+      "learning_rate": 0.009592000000000002,
+      "loss": 4.5277734375,
+      "step": 1200
+    },
+    {
+      "epoch": 0.026,
+      "grad_norm": 0.20846614241600037,
+      "learning_rate": 0.010391999999999998,
+      "loss": 4.486420288085937,
+      "step": 1300
+    },
+    {
+      "epoch": 0.028,
+      "grad_norm": 0.16785487532615662,
+      "learning_rate": 0.011192,
+      "loss": 4.471618041992188,
+      "step": 1400
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.17252753674983978,
+      "learning_rate": 0.011992000000000001,
+      "loss": 4.429487915039062,
+      "step": 1500
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 0.42827746272087097,
+      "learning_rate": 0.012792,
+      "loss": 4.423707885742187,
+      "step": 1600
+    },
+    {
+      "epoch": 0.034,
+      "grad_norm": 0.18584232032299042,
+      "learning_rate": 0.013592,
+      "loss": 4.405695190429688,
+      "step": 1700
+    },
+    {
+      "epoch": 0.036,
+      "grad_norm": 0.1389407366514206,
+      "learning_rate": 0.014392,
+      "loss": 4.381403503417968,
+      "step": 1800
+    },
+    {
+      "epoch": 0.038,
+      "grad_norm": 0.17971371114253998,
+      "learning_rate": 0.015192,
+      "loss": 4.340931091308594,
+      "step": 1900
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.1317117065191269,
+      "learning_rate": 0.015992,
+      "loss": 4.357503356933594,
+      "step": 2000
+    },
+    {
+      "epoch": 0.04,
+      "eval_accuracy": 0.27022504892367905,
+      "eval_loss": 4.341521739959717,
+      "eval_runtime": 4.6212,
+      "eval_samples_per_second": 216.396,
+      "eval_steps_per_second": 1.731,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 50000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9223372036854775807,
+  "save_steps": 2000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:870f39a3db1401b65049dd32abdbe4a59cc37833fb76a05eadfa7e488ee0da3c
+size 5265