Training in progress, step 6500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb3011d25fd85a465cf3e0ce6a9bcc74aa9316f6611f88f06f23c17f5dd203b1
+oid sha256:1f3a276466a33703f196db9593f8616ba67208e582231cd2a03b650321aa4d53
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8080d252b62a6ceb80eef3556d6b8ddb39639a5625e1d88dd9cc1e6ce9ba8af8
+oid sha256:1b0abef78c4ed7dfb98b086df2dddeeae40bfd7eaa1fd9b7823a0cefd916c5c1
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3e29c5cf029c43a0b9eb6818343605a4d54765fc02cea34588573e488f22ffd
+oid sha256:2ab84c23d1ad7d744482de62386d239d16dc2019b5055dd768ecb135e64d3f32
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:260e81eea4566c115fd02bd1907dd188f736d221da2bd52f057ef75265ae93af
+oid sha256:18ff421a3032a7b1069b9c0436162504eb328a8b10771ab86c67b9636c0012fb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.5906735751295336,
+  "epoch": 2.8065630397236614,
   "eval_steps": 500,
-  "global_step": 6000,
+  "global_step": 6500,
   "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
     },
     {
@@ -107,6 +107,13 @@
       "learning_rate": 2.734599884858952e-06,
       "loss": 0.3428,
       "step": 6000
+    },
+    {
+      "epoch": 2.8065630397236614,
+      "grad_norm": 0.8941567540168762,
+      "learning_rate": 1.2982153137593554e-06,
+      "loss": 0.353,
+      "step": 6500
     }
   ],
   "logging_steps": 500,
@@ -126,7 +133,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.461377145765888e+16,
+  "total_flos": 1.583168723877888e+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