Training in progress, step 350, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f094722188717075439138e1e791728eb83dc89ede5725094ba20a9394827cb
+oid sha256:e64c8f22073f810e14ea11a51c997d214e79493ceb718231c712f6890686cd0a
 size 2066752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13798eed199d0e8f7d444eff9af7f40acdebc84529bd74f913cce85929e905b5
+oid sha256:5f58b607dd2bb3376b1a270f24d36d7e6ad6b3fbcf77fb0f3a3fa5f5a10a5ee3
 size 2162798

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0eaa843a45d8e738cee2ae0531250a101659f24a1b6fb71ecb838949839be942
+oid sha256:cb5daaf1199744204be7b2c0227bbbc86b8f02198eb2753856850454b418ba43
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:946dbb58346f352ba6907add2b54217151d2cb0118b1f9eb15982ba30ba98cc3
+oid sha256:0ef0a11ec368bc2c0da98c701c736f96e203337d9c97fab18e13b92ce5dd6d5b
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c62f46b6ecdcc9452fbe00042ae2d6095daf65d97a17c5763e0d0ed253cea52
+oid sha256:972684576ff55802aec9ad573b837fe663d45ec783d38050b5b6dc1fc7271117
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 23.076923076923077,
+  "epoch": 26.923076923076923,
   "eval_steps": 50,
-  "global_step": 300,
+  "global_step": 350,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -273,6 +273,49 @@
       "eval_samples_per_second": 284.199,
       "eval_steps_per_second": 4.544,
       "step": 300
+    },
+    {
+      "epoch": 23.846153846153847,
+      "grad_norm": 0.412109375,
+      "learning_rate": 0.00010275543423681621,
+      "loss": 9.2185,
+      "step": 310
+    },
+    {
+      "epoch": 24.615384615384617,
+      "grad_norm": 0.4140625,
+      "learning_rate": 9.724456576318381e-05,
+      "loss": 9.2101,
+      "step": 320
+    },
+    {
+      "epoch": 25.384615384615383,
+      "grad_norm": 0.412109375,
+      "learning_rate": 9.174206545276677e-05,
+      "loss": 9.2002,
+      "step": 330
+    },
+    {
+      "epoch": 26.153846153846153,
+      "grad_norm": 0.416015625,
+      "learning_rate": 8.626464421815919e-05,
+      "loss": 9.193,
+      "step": 340
+    },
+    {
+      "epoch": 26.923076923076923,
+      "grad_norm": 0.41015625,
+      "learning_rate": 8.082893680762619e-05,
+      "loss": 9.1896,
+      "step": 350
+    },
+    {
+      "epoch": 26.923076923076923,
+      "eval_loss": 9.20389461517334,
+      "eval_runtime": 5.2643,
+      "eval_samples_per_second": 285.129,
+      "eval_steps_per_second": 4.559,
+      "step": 350
     }
   ],
   "logging_steps": 10,
@@ -292,7 +335,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 122747564851200.0,
+  "total_flos": 143205492326400.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null