Training in progress, step 1000

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bd21bd8e8d3182f7f75a886b6557fe155dfd7dd1572b059e68dbe9cdcfd5705
+oid sha256:cdfacc0d200e99d738052580fb890ca33665de7eaa76e19e0033c66446adef98
 size 268290900

run-2/checkpoint-1000/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:151add0d49f79564d60aac47973c4872cacc2c8d698d1f97076fc8cea9a451a1
-size 2056020
+oid sha256:cdfacc0d200e99d738052580fb890ca33665de7eaa76e19e0033c66446adef98
+size 268290900

run-2/checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e40ad42f5bc4a64b5b288a43e45dc19844fae9ef64a43d1e3ac242f8ff4f0ec9
+size 536643898

run-2/checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbeee5483b3473d40884032dbdc7615fd67ccf004ea5660dd5b8668c9c4e48a0
+size 14244

run-2/checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd6312bafb4f172d36cde8e97f0ddfa67db03a0e6d8fc98f230d4474ba8ee580
+size 1064

run-2/checkpoint-1000/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-2/checkpoint-1000/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-2/checkpoint-1000/trainer_state.json

@@ -0,0 +1,63 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.1446540880503147,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.2003006935119629,
+      "eval_runtime": 3.3177,
+      "eval_samples_per_second": 934.389,
+      "eval_steps_per_second": 19.592,
+      "step": 318
+    },
+    {
+      "epoch": 1.57,
+      "grad_norm": 0.5493956804275513,
+      "learning_rate": 1.371069182389937e-05,
+      "loss": 0.3146,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.10496184974908829,
+      "eval_runtime": 3.3448,
+      "eval_samples_per_second": 926.816,
+      "eval_steps_per_second": 19.433,
+      "step": 636
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.07582292705774307,
+      "eval_runtime": 3.4125,
+      "eval_samples_per_second": 908.413,
+      "eval_steps_per_second": 19.047,
+      "step": 954
+    },
+    {
+      "epoch": 3.14,
+      "grad_norm": 0.5040295124053955,
+      "learning_rate": 7.421383647798742e-06,
+      "loss": 0.1211,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1590,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 260941334653608.0,
+  "train_batch_size": 48,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.80288090122901,
+    "num_train_epochs": 7,
+    "temperature": 17
+  }
+}

run-2/checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4ef4d6f9f8144b6a0d57a691210e77bd9f5c55ff53f926c5e4cbe0cbfb35bbb
+size 4984