Training in progress, step 5500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8afb0d0b62fb8f8adb16f60cebb6969e5414b2b50bde9032dc6f0c72628c9dd5
+oid sha256:683c6b844253214d5535f32fb10d971f05c91a8acc294539eaa07b28c3f16d01
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c295cb3bd087782a69e7f91b4c751374121547d550731b924797acc49b972f4f
+oid sha256:5e606906707907082dc8c6184eedbdf1ad6410646fdfb29ec0957ff6b4fea464
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4003991bac902b1da67d2e0a6f5247852d67aac63d9d9b8f258b567318e58b14
+oid sha256:cd16ada593cf0a36458682125206d81fb88aab5b155751c1343bff1314ca90c7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b2ef6858e3f6e1355f840e4b63fbaab758a6bc5dd790e378e61672a918d4f82
+oid sha256:33ec81ecd0f74edad60756c692726503a5467d4d5a63f6abe2c6e32cac418cdc
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.158894645941278,
+  "epoch": 2.3747841105354057,
   "eval_steps": 500,
-  "global_step": 5000,
+  "global_step": 5500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -39,9 +39,9 @@
     {
       "epoch": 1.0,
       "eval_loss": 0.33670297265052795,
-      "eval_runtime": 28.3351,
-      "eval_samples_per_second": 16.658,
-      "eval_steps_per_second": 4.164,
+      "eval_runtime": 28.2248,
+      "eval_samples_per_second": 16.723,
+      "eval_steps_per_second": 4.181,
       "step": 2316
     },
     {
@@ -82,9 +82,9 @@
     {
       "epoch": 2.0,
       "eval_loss": 0.3095574975013733,
-      "eval_runtime": 28.3225,
-      "eval_samples_per_second": 16.665,
-      "eval_steps_per_second": 4.166,
+      "eval_runtime": 28.2419,
+      "eval_samples_per_second": 16.713,
+      "eval_steps_per_second": 4.178,
       "step": 4632
     },
     {
@@ -93,6 +93,13 @@
       "learning_rate": 5.613126079447323e-06,
       "loss": 0.3467,
       "step": 5000
+    },
+    {
+      "epoch": 2.3747841105354057,
+      "grad_norm": 0.6125323176383972,
+      "learning_rate": 4.173862982153138e-06,
+      "loss": 0.3513,
+      "step": 5500
     }
   ],
   "logging_steps": 500,
@@ -112,7 +119,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.217793989541888e+16,
+  "total_flos": 1.339585567653888e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0589186e917e79226308cded95843db5013776fee27e83a39d678ba03ec762d3
+oid sha256:d2d71d788b491a41c54d3b024285748be4a2e443d732e96343f48dd9941e304a
 size 5432