Training in progress, epoch 1, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35c2099539a14d0414c4a5333e82e425d5e936f56bd1431227ce15e1466638b9
+oid sha256:a5990468375083d2d44289b05135a6192d533a8e788b77ae1daac92644955e56
 size 500979600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e060e0b8662097f2c7a341148231cc0ad251615f47b387655c29d78b8c72400a
+oid sha256:9b54aa78399d23de4fbb5f625c787c823a4cf1c373bdc55dc8441636e3f6900b
 size 1002078330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86a1ccd9f7066dca55443398dffdd4e76ff6f9b9071f99d8222f75921367ac98
+oid sha256:243bed054e6ca95566a31f84929c545f9505688d6a662df2d1ba4f4954f9e518
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6602c18a1ebe894c1d51ce5c9cea3744db091c466423f123d4fa8b7754d9378a
+oid sha256:57298e368684a7f74b8580ab500ef876b797e959380e8c09da0e2d665556ed4b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,63 +1,34 @@
 {
-  "best_metric": 0.9163894057273865,
-  "best_model_checkpoint": "./opt_trained3/checkpoint-2720",
-  "epoch": 1.99898924928788,
+  "best_metric": 0.9048793911933899,
+  "best_model_checkpoint": "./opt_trained3/checkpoint-1361",
+  "epoch": 1.0,
   "eval_steps": 500,
-  "global_step": 2720,
+  "global_step": 1361,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.3675457134981163,
-      "grad_norm": 1.09419846534729,
+      "grad_norm": 1.054343342781067,
       "learning_rate": 9.189154158168292e-05,
-      "loss": 0.9262,
+      "loss": 0.9192,
       "step": 500
     },
     {
       "epoch": 0.7350914269962326,
-      "grad_norm": 1.0400797128677368,
+      "grad_norm": 1.1676549911499023,
       "learning_rate": 7.019605024359474e-05,
-      "loss": 0.9246,
+      "loss": 0.9147,
       "step": 1000
     },
     {
       "epoch": 1.0,
-      "eval_loss": 0.9197561740875244,
-      "eval_runtime": 761.7722,
-      "eval_samples_per_second": 50.796,
-      "eval_steps_per_second": 12.699,
+      "eval_loss": 0.9048793911933899,
+      "eval_runtime": 768.112,
+      "eval_samples_per_second": 50.377,
+      "eval_steps_per_second": 12.595,
       "step": 1361
-    },
-    {
-      "epoch": 1.1021777083524764,
-      "grad_norm": 0.9448853135108948,
-      "learning_rate": 4.195020556092935e-05,
-      "loss": 0.9181,
-      "step": 1500
-    },
-    {
-      "epoch": 1.4697234218505928,
-      "grad_norm": 0.8499826788902283,
-      "learning_rate": 1.631521781767214e-05,
-      "loss": 0.9169,
-      "step": 2000
-    },
-    {
-      "epoch": 1.837269135348709,
-      "grad_norm": 0.787797749042511,
-      "learning_rate": 1.6054963006338742e-06,
-      "loss": 0.9153,
-      "step": 2500
-    },
-    {
-      "epoch": 1.99898924928788,
-      "eval_loss": 0.9163894057273865,
-      "eval_runtime": 762.3921,
-      "eval_samples_per_second": 50.755,
-      "eval_steps_per_second": 12.689,
-      "step": 2720
     }
   ],
   "logging_steps": 500,
@@ -72,12 +43,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.37491227277056e+17,
+  "total_flos": 6.8780176144128e+16,
   "train_batch_size": 32,
   "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:ae610ca3ba358abeebc6af3521a544fd6c45bd94a76da5a597144463f080a452
+oid sha256:a452ae32a30f3ff55dc4f63985dae2c59ba5cf468734128941ae47abda2b6cbd
 size 5368