Training in progress, epoch 3, checkpoint

last-checkpoint/config.json

@@ -2024,6 +2024,6 @@
   "pooler_output_size": 768,
   "problem_type": "single_label_classification",
   "qkv_bias": true,
-  "transformers_version": "5.0.0",
+  "transformers_version": "5.2.0",
   "use_cache": false
 }

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09d8c13da6fc8f3864dc1e4f9d37dbc37b1ee5fa25aac6b822a1d00236a31b10
+oid sha256:73ddd37e82ad9b070acf536f9c7aa7816854a295a50816155c2e61f31ea7fae5
 size 346293856

last-checkpoint/trainer_state.json

@@ -1,37 +1,83 @@
 {
-  "best_global_step": 1,
-  "best_metric": 0.7093276977539062,
-  "best_model_checkpoint": "./finetuning/checkpoint-1",
-  "epoch": 1.0,
+  "best_global_step": 32,
+  "best_metric": 1.1013036966323853,
+  "best_model_checkpoint": "./finetuning/checkpoint-32",
+  "epoch": 3.0,
   "eval_steps": 500,
-  "global_step": 1,
+  "global_step": 48,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
+    {
+      "epoch": 0.625,
+      "grad_norm": 2.963273286819458,
+      "learning_rate": 4.71875e-05,
+      "loss": 1.1393531799316405,
+      "step": 10
+    },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5,
-      "eval_loss": 0.7093276977539062,
-      "eval_runtime": 1.0358,
-      "eval_samples_per_second": 1.931,
-      "eval_steps_per_second": 0.965,
-      "step": 1
+      "eval_accuracy": 0.7275,
+      "eval_loss": 1.117279052734375,
+      "eval_runtime": 99.7594,
+      "eval_samples_per_second": 20.048,
+      "eval_steps_per_second": 1.253,
+      "step": 16
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 1.9508087635040283,
+      "learning_rate": 4.40625e-05,
+      "loss": 0.8301602363586426,
+      "step": 20
+    },
+    {
+      "epoch": 1.875,
+      "grad_norm": 1.7418757677078247,
+      "learning_rate": 4.09375e-05,
+      "loss": 0.5593328952789307,
+      "step": 30
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.733,
+      "eval_loss": 1.1013036966323853,
+      "eval_runtime": 99.7792,
+      "eval_samples_per_second": 20.044,
+      "eval_steps_per_second": 1.253,
+      "step": 32
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 1.2206847667694092,
+      "learning_rate": 3.78125e-05,
+      "loss": 0.4049041271209717,
+      "step": 40
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.729,
+      "eval_loss": 1.130679965019226,
+      "eval_runtime": 98.8399,
+      "eval_samples_per_second": 20.235,
+      "eval_steps_per_second": 1.265,
+      "step": 48
     }
   ],
   "logging_steps": 10,
-  "max_steps": 10,
+  "max_steps": 160,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 10,
   "save_steps": 500,
   "stateful_callbacks": {
     "EarlyStoppingCallback": {
       "args": {
-        "early_stopping_patience": 2,
+        "early_stopping_patience": 4,
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -45,8 +91,8 @@
       "attributes": {}
     }
   },
-  "total_flos": 625481093873664.0,
-  "train_batch_size": 256,
+  "total_flos": 1.876443281620992e+18,
+  "train_batch_size": 512,
   "trial_name": null,
   "trial_params": null
 }

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4242ddf0c92c5ca117be896f7e39a66ca1652c7cf4d4a14f418fb7278dbd076c
-size 5201
+oid sha256:15bd58ced891c43674dae43ad5d77ad1ff23c75b4ce3fd15a3acd656eaa2e3e6
+size 4792