Training in progress, step 1000, checkpoint

last-checkpoint/config.json

@@ -19,7 +19,7 @@
   "num_hidden_layers": 12,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
-  "transformers_version": "4.57.3",
+  "transformers_version": "4.57.1",
   "type_vocab_size": 1,
   "use_cache": true,
   "vocab_size": 50265

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42690867e778f4db141a39c02caa1a4a181fb1838de64648f76992024bb090d6
+oid sha256:ce27503682001cc084908a25069dc678057168cae01004ca3bff7b72c191e7e4
 size 498612824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cee156cc7324a335bd0cf2e1fa7a6de4b52ebb3d6ee59259f88882100a16a0a
+oid sha256:32cf9b47bd2f0d00e8d39cadaaf61447f1198c75e8548dd4428f2a9031563387
 size 997345931

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed290419ddbbaf4c4f46d92ab98980c1b33e3e9b93e34d7bc94d8d13097423b4
+oid sha256:f2ce5645288f483e7a9daa2c7a16180a6531e36418232835ffee5a4fecb21062
 size 1465

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_global_step": 1000,
-  "best_metric": 0.10802757740020752,
+  "best_metric": 0.08424179255962372,
   "best_model_checkpoint": "./training_output/checkpoint-1000",
-  "epoch": 0.05,
+  "epoch": 0.125,
   "eval_steps": 1000,
   "global_step": 1000,
   "is_hyper_param_search": false,
@@ -10,31 +10,31 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.025,
-      "grad_norm": 0.8834348917007446,
-      "learning_rate": 1.9501000000000002e-05,
-      "loss": 0.1437,
+      "epoch": 0.0625,
+      "grad_norm": 33.47822570800781,
+      "learning_rate": 1.8752500000000004e-05,
+      "loss": 0.1408,
       "step": 500
     },
     {
-      "epoch": 0.05,
-      "grad_norm": 9.513919830322266,
-      "learning_rate": 1.9001e-05,
-      "loss": 0.1085,
+      "epoch": 0.125,
+      "grad_norm": 66.1669692993164,
+      "learning_rate": 1.7502500000000004e-05,
+      "loss": 0.1244,
       "step": 1000
     },
     {
-      "epoch": 0.05,
-      "eval_accuracy": 0.91835,
-      "eval_loss": 0.10802757740020752,
-      "eval_runtime": 381.1922,
-      "eval_samples_per_second": 52.467,
-      "eval_steps_per_second": 3.279,
+      "epoch": 0.125,
+      "eval_accuracy": 0.931,
+      "eval_loss": 0.08424179255962372,
+      "eval_runtime": 148.5886,
+      "eval_samples_per_second": 53.84,
+      "eval_steps_per_second": 3.365,
       "step": 1000
     }
   ],
   "logging_steps": 500,
-  "max_steps": 20000,
+  "max_steps": 8000,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 1000,

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4672bef08597eaac4166af409003080f023f24990f8f58c185b2b990119dc93e
+oid sha256:5d1dcf0aa731896a45dc92ce645a0147a079fc2db258f2967bafe27b497eba6b
 size 5841