Training in progress, step 300, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ee790394f53b15b34064b0939918e9c8b9072447adc2a80ca76e194e588ef77
+oid sha256:2ef91c402a00a0ab5044139adeab6e6c84327ec20dcb98519a5dd47c13459484
 size 2066752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b600d0fdd76816945ac85cd28656988ce013a6ca21972288d9510ea639a3b024
+oid sha256:cb179df1153cc6ae95ee73badb83521bc1538bf7cfc4bae63de17a2839c6501c
 size 2162798

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6573f71e16a24783361451616c22fd04c27282b0b2e2a2e59843f152dcef4214
+oid sha256:4c3d9a056933457acb03adc6fbca244787e41f8774a88cacdd231cad1f4c1462
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecf0e28c99191538a3c32f9899d55726f4960b122972e130d2555f6280416517
+oid sha256:b8232c83a30fb4990d5c536090c2c4b7a61c630c74ed4091730cf211a2c322f3
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa6ea3f731b59c0eb2ad9a4603b6f27b0a7e78ff027cc2874370bdf6bfc7598e
+oid sha256:4c62f46b6ecdcc9452fbe00042ae2d6095daf65d97a17c5763e0d0ed253cea52
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 21.53846153846154,
+  "epoch": 23.076923076923077,
   "eval_steps": 40,
-  "global_step": 280,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -267,6 +267,20 @@
       "eval_samples_per_second": 280.313,
       "eval_steps_per_second": 4.482,
       "step": 280
+    },
+    {
+      "epoch": 22.307692307692307,
+      "grad_norm": 0.404296875,
+      "learning_rate": 0.00011373535578184082,
+      "loss": 9.2496,
+      "step": 290
+    },
+    {
+      "epoch": 23.076923076923077,
+      "grad_norm": 0.40625,
+      "learning_rate": 0.00010825793454723325,
+      "loss": 9.2338,
+      "step": 300
     }
   ],
   "logging_steps": 10,
@@ -286,7 +300,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 114564393861120.0,
+  "total_flos": 122747564851200.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null