Training in progress, step 580, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e938d2e6c79fd63eb1bf7556472b175170f1e1fcb7490186628ef3502bcb601
+oid sha256:d8a29143396eec77d41eb67970e181bc16a75b0dbc3fc41d874e883a617b530f
 size 2066752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6afdd36c2c13a653549d0d71f18e3e7d5187494fb4c71994a47849ec6c82bbff
+oid sha256:36523e64f00628b69639a58b0773985da9c069029b6cd768dfa76d4a8b7484ca
 size 2162798

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa472c1d2e1ad30011add0ce83904e37d2caa36216037fbad49576f2756efb5b
+oid sha256:2ea48777c657ab2eaff790b1967aab8c9a1afa8e0f83ce703776ac81a04df427
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:743d3a9f693b684ee3153d836a21fe12defa659ab9ab57ee619a05a569102f6c
+oid sha256:271b74e66e71309f5334c1d7cc17a4a6232d396cc34f548747450ef9fdb432db
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1c1b0efcf3afa634fda84640ee52e51b8f239aa7ea918845652fbaccafc77f8
+oid sha256:84a0942ceea86ba4bd54997340637a60ac64ad5dfb513f2f4420905351033838
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 43.07692307692308,
+  "epoch": 44.61538461538461,
   "eval_steps": 40,
-  "global_step": 560,
+  "global_step": 580,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -519,6 +519,20 @@
       "eval_samples_per_second": 284.561,
       "eval_steps_per_second": 4.55,
       "step": 560
+    },
+    {
+      "epoch": 43.84615384615385,
+      "grad_norm": 0.41796875,
+      "learning_rate": 1.3638696597277679e-06,
+      "loss": 9.1777,
+      "step": 570
+    },
+    {
+      "epoch": 44.61538461538461,
+      "grad_norm": 0.419921875,
+      "learning_rate": 6.069322682050516e-07,
+      "loss": 9.1766,
+      "step": 580
     }
   ],
   "logging_steps": 10,
@@ -538,7 +552,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 229128787722240.0,
+  "total_flos": 237311958712320.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null