Training in progress, epoch 1, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b6be78a2dd0e0be68c245a8d4a9b9ccfeb5c50e5371c60c58cfea0e0459f51a
+oid sha256:77a43afa5413209488282deaba8f3e6de65e3901e35bdafd4f239b63a96e4c53
 size 500979600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23709651cc0736566b6cf6e31352814a96bb51f7ed34d31167879425e695e042
+oid sha256:cf433d541d14e0716f77c5d6992896aed2f222236bee78e7fc2cb9d99f58d9e7
 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 sha256:9ce2a9fef65681ae0027502eaf6f2b8935ec5c8dbe0972fb30de040f99f9d624
+oid sha256:902ae1f31337b1589c09fb3fa5e1c9d37d43036b50a2a55706a5b53db24b476c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,92 +1,20 @@
 {
-  "best_metric": 0.5374372005462646,
-  "best_model_checkpoint": "./opt_trained3/checkpoint-60",
-  "epoch": 9.353982300884956,
+  "best_metric": 0.535097062587738,
+  "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": 0.5505019426345825,
-      "eval_runtime": 5.9848,
-      "eval_samples_per_second": 50.127,
-      "eval_steps_per_second": 12.532,
+      "eval_loss": 0.535097062587738,
+      "eval_runtime": 6.0207,
+      "eval_samples_per_second": 49.828,
+      "eval_steps_per_second": 12.457,
       "step": 15
-    },
-    {
-      "epoch": 2.0,
-      "eval_loss": 0.5414664149284363,
-      "eval_runtime": 5.9806,
-      "eval_samples_per_second": 50.162,
-      "eval_steps_per_second": 12.541,
-      "step": 30
-    },
-    {
-      "epoch": 3.0,
-      "eval_loss": 0.5381864309310913,
-      "eval_runtime": 5.9811,
-      "eval_samples_per_second": 50.158,
-      "eval_steps_per_second": 12.539,
-      "step": 45
-    },
-    {
-      "epoch": 4.0,
-      "eval_loss": 0.5374372005462646,
-      "eval_runtime": 5.9965,
-      "eval_samples_per_second": 50.03,
-      "eval_steps_per_second": 12.507,
-      "step": 60
-    },
-    {
-      "epoch": 5.0,
-      "eval_loss": 0.5423746705055237,
-      "eval_runtime": 5.9878,
-      "eval_samples_per_second": 50.102,
-      "eval_steps_per_second": 12.525,
-      "step": 75
-    },
-    {
-      "epoch": 6.0,
-      "eval_loss": 0.5467855930328369,
-      "eval_runtime": 5.9773,
-      "eval_samples_per_second": 50.19,
-      "eval_steps_per_second": 12.547,
-      "step": 90
-    },
-    {
-      "epoch": 7.0,
-      "eval_loss": 0.5484521389007568,
-      "eval_runtime": 5.9799,
-      "eval_samples_per_second": 50.168,
-      "eval_steps_per_second": 12.542,
-      "step": 105
-    },
-    {
-      "epoch": 8.0,
-      "eval_loss": 0.548169732093811,
-      "eval_runtime": 5.9928,
-      "eval_samples_per_second": 50.06,
-      "eval_steps_per_second": 12.515,
-      "step": 120
-    },
-    {
-      "epoch": 9.0,
-      "eval_loss": 0.5496641993522644,
-      "eval_runtime": 5.9832,
-      "eval_samples_per_second": 50.141,
-      "eval_steps_per_second": 12.535,
-      "step": 135
-    },
-    {
-      "epoch": 9.353982300884956,
-      "eval_loss": 0.5497786998748779,
-      "eval_runtime": 6.0047,
-      "eval_samples_per_second": 49.961,
-      "eval_steps_per_second": 12.49,
-      "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 sha256:788e7fe2058ffdb6f5cc8f4de5c3cd3cb908c383f75a94fdc394dfc29b2dad1a
+oid sha256:da1113fb33b5dc52d2cd8aa9933b02ed905b55e4f161767b2b195fd21d946a9d
 size 5368