Training in progress, step 2000, checkpoint

last-checkpoint/config.json

@@ -19,7 +19,7 @@
   "num_hidden_layers": 12,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
-  "transformers_version": "4.57.1",
+  "transformers_version": "4.57.3",
   "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:ce27503682001cc084908a25069dc678057168cae01004ca3bff7b72c191e7e4
+oid sha256:4a15bc84d864fdbb853c377342871766d01db1ca734cbc9099f34ff07ef54be9
 size 498612824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32cf9b47bd2f0d00e8d39cadaaf61447f1198c75e8548dd4428f2a9031563387
+oid sha256:bb80b28a5278923852405f44924f6cd1910649368efcf731583ea9a028e542d0
 size 997345931

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41afff64258c100464839a9401c63f65038ccc9dbd2dd2c5f61f68f3b93f2b79
+oid sha256:8cbb9d20ae0e060525bcac1b70551f336242a3392c3ba0392910b81075e6dc33
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14ae2a2128444abab378aa06c09a61a84665f758fcc19fc46f5789b0bc1b5665
+oid sha256:f4aa03f6e0cd07cf67ce1fbe3101d545f5771ef9148b9debf02b11cf6948da5c
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2ce5645288f483e7a9daa2c7a16180a6531e36418232835ffee5a4fecb21062
+oid sha256:f8cac132f6cb7e26c16168d7dd2d5889b5966954ea1f2f629ae0cf0022b48d02
 size 1465

last-checkpoint/trainer_state.json

@@ -1,40 +1,63 @@
 {
   "best_global_step": 1000,
-  "best_metric": 0.08424179255962372,
+  "best_metric": 0.10802757740020752,
   "best_model_checkpoint": "./training_output/checkpoint-1000",
-  "epoch": 0.125,
+  "epoch": 0.1,
   "eval_steps": 1000,
-  "global_step": 1000,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.0625,
-      "grad_norm": 33.47822570800781,
-      "learning_rate": 1.8752500000000004e-05,
-      "loss": 0.1408,
+      "epoch": 0.025,
+      "grad_norm": 0.8834348917007446,
+      "learning_rate": 1.9501000000000002e-05,
+      "loss": 0.1437,
       "step": 500
     },
     {
-      "epoch": 0.125,
-      "grad_norm": 66.1669692993164,
-      "learning_rate": 1.7502500000000004e-05,
-      "loss": 0.1244,
+      "epoch": 0.05,
+      "grad_norm": 9.513919830322266,
+      "learning_rate": 1.9001e-05,
+      "loss": 0.1085,
       "step": 1000
     },
     {
-      "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,
+      "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,
       "step": 1000
+    },
+    {
+      "epoch": 0.075,
+      "grad_norm": 0.013394818641245365,
+      "learning_rate": 1.8501e-05,
+      "loss": 0.0965,
+      "step": 1500
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.017180055379867554,
+      "learning_rate": 1.8001000000000003e-05,
+      "loss": 0.0716,
+      "step": 2000
+    },
+    {
+      "epoch": 0.1,
+      "eval_accuracy": 0.8473,
+      "eval_loss": 0.25237375497817993,
+      "eval_runtime": 381.1616,
+      "eval_samples_per_second": 52.471,
+      "eval_steps_per_second": 3.279,
+      "step": 2000
     }
   ],
   "logging_steps": 500,
-  "max_steps": 8000,
+  "max_steps": 20000,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 1000,
@@ -50,7 +73,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1052444221440000.0,
+  "total_flos": 2104888442880000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

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