Training in progress, step 480, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be10d176282a6dad55fe521c2659a5c756cd8682fe7880e2f3107339f0e4de62
+oid sha256:1d7ea76a7fe9a3a72bfd9d91b402405835199ee3276e58a75b2b90de4df6faf3
 size 2066752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb15b49ee20c5f76489e72b92694abdc408eb4ce3362d919c3b6d1a7196e9074
+oid sha256:55accac051f9670b17e34e185dbc7868d482bf70ed6d173806a6b70a0e363569
 size 2162798

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:300d6be6a0627e29641baf29e49bd0ac9ea099599f21c9aa61bbfba24527c848
+oid sha256:470231bc1b9887c06a948023513b621d90c9fafd020c42706547857cecbea47a
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00edd3e36fd88028498581207c7af1930a5e4dbdf2075dd176fd55407ffe344f
+oid sha256:6f6c57457d54b7bbc2f9492e8a647b031ace734fd264dd50bf21159a960787c9
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:776adfde0d7f584a3b4ff8a307fb88545361f677ac68f090fa018fdc36afaca7
+oid sha256:c43ae2edd3b792abc4b0bbe5b96b0cbff30dfd7f8da70e732cd4ef7bf6a1ef4a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 35.38461538461539,
+  "epoch": 36.92307692307692,
   "eval_steps": 40,
-  "global_step": 460,
+  "global_step": 480,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -425,6 +425,28 @@
       "learning_rate": 2.8321748683154893e-05,
       "loss": 9.1782,
       "step": 460
+    },
+    {
+      "epoch": 36.15384615384615,
+      "grad_norm": 0.419921875,
+      "learning_rate": 2.4589339022310386e-05,
+      "loss": 9.1783,
+      "step": 470
+    },
+    {
+      "epoch": 36.92307692307692,
+      "grad_norm": 0.416015625,
+      "learning_rate": 2.1085949060360654e-05,
+      "loss": 9.1768,
+      "step": 480
+    },
+    {
+      "epoch": 36.92307692307692,
+      "eval_loss": 9.194061279296875,
+      "eval_runtime": 5.2795,
+      "eval_samples_per_second": 284.308,
+      "eval_steps_per_second": 4.546,
+      "step": 480
     }
   ],
   "logging_steps": 10,
@@ -444,7 +466,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 188212932771840.0,
+  "total_flos": 196396103761920.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null