Training in progress, epoch 1, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:355b00ffa8e07d4346760e95eccf2eb530e9a1b84d8356dcbf28db9cd7dd5295
+oid sha256:2d6430e4a6208a8112bffb365eeaa287b4691166600fb665cd625816e4b96a8c
 size 500979600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c08f01c9be95dfaa9d09755bce204473729e762258d21a0f4b953c864ea7e68
+oid sha256:9f72b21dc6b023992f07d421fba6e4e2b690747ea68d2145d3c66dabae86e00e
 size 1002078330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b00502da5feba7cd8100a8570af5fac37e5c8c267a539c58346d380c13e441c
+oid sha256:574024fd0bef58b4ca8af0606c1be9cf07d7494e9e30913df874b1f6896f01c2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8c98fcf42f494fa75f135fb338a20acefff4d78f4f44abc68b10fde88458a02
+oid sha256:5d4270c057ffbe7d94d3a4a46e15a61be9cfe5f3368f1f48731c220c26ede867
 size 1064

last-checkpoint/trainer_state.json

@@ -1,92 +1,20 @@
 {
-  "best_metric": 0.6704908013343811,
-  "best_model_checkpoint": "./opt_trained3/checkpoint-140",
-  "epoch": 9.353982300884956,
+  "best_metric": 0.6533264517784119,
+  "best_model_checkpoint": "./opt_trained3/checkpoint-15",
+  "epoch": 1.0,
   "eval_steps": 500,
-  "global_step": 140,
+  "global_step": 15,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.7184422016143799,
-      "eval_runtime": 5.9548,
-      "eval_samples_per_second": 50.38,
-      "eval_steps_per_second": 12.595,
+      "eval_loss": 0.6533264517784119,
+      "eval_runtime": 5.9687,
+      "eval_samples_per_second": 50.262,
+      "eval_steps_per_second": 12.565,
       "step": 15
-    },
-    {
-      "epoch": 2.0,
-      "eval_loss": 0.7095981240272522,
-      "eval_runtime": 5.9501,
-      "eval_samples_per_second": 50.419,
-      "eval_steps_per_second": 12.605,
-      "step": 30
-    },
-    {
-      "epoch": 3.0,
-      "eval_loss": 0.6935510039329529,
-      "eval_runtime": 5.9572,
-      "eval_samples_per_second": 50.359,
-      "eval_steps_per_second": 12.59,
-      "step": 45
-    },
-    {
-      "epoch": 4.0,
-      "eval_loss": 0.6844949126243591,
-      "eval_runtime": 5.9603,
-      "eval_samples_per_second": 50.333,
-      "eval_steps_per_second": 12.583,
-      "step": 60
-    },
-    {
-      "epoch": 5.0,
-      "eval_loss": 0.6744114756584167,
-      "eval_runtime": 5.9487,
-      "eval_samples_per_second": 50.432,
-      "eval_steps_per_second": 12.608,
-      "step": 75
-    },
-    {
-      "epoch": 6.0,
-      "eval_loss": 0.6723850965499878,
-      "eval_runtime": 5.9492,
-      "eval_samples_per_second": 50.427,
-      "eval_steps_per_second": 12.607,
-      "step": 90
-    },
-    {
-      "epoch": 7.0,
-      "eval_loss": 0.6734561920166016,
-      "eval_runtime": 5.9536,
-      "eval_samples_per_second": 50.39,
-      "eval_steps_per_second": 12.598,
-      "step": 105
-    },
-    {
-      "epoch": 8.0,
-      "eval_loss": 0.6707628965377808,
-      "eval_runtime": 5.9562,
-      "eval_samples_per_second": 50.368,
-      "eval_steps_per_second": 12.592,
-      "step": 120
-    },
-    {
-      "epoch": 9.0,
-      "eval_loss": 0.670530378818512,
-      "eval_runtime": 5.9504,
-      "eval_samples_per_second": 50.417,
-      "eval_steps_per_second": 12.604,
-      "step": 135
-    },
-    {
-      "epoch": 9.353982300884956,
-      "eval_loss": 0.6704908013343811,
-      "eval_runtime": 5.9917,
-      "eval_samples_per_second": 50.069,
-      "eval_steps_per_second": 12.517,
-      "step": 140
     }
   ],
   "logging_steps": 500,
@@ -101,12 +29,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 5207869157760000.0,
+  "total_flos": 556605613440000.0,
   "train_batch_size": 24,
   "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:ce5b37466798b22cd1c58fa164a2deb26fd86f95d9733731d6588e8abd389d38
+oid sha256:20903957dfffb8df7a5a23888baadcd68fb6b87201bf4873082dc166ef1b5bc9
 size 5368