Training in progress, step 350, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb3944baba224fb9f68ab01233170ab280c7bca8803f3c7e71a714c5f3fdcf93
+oid sha256:e4cbb235c853766b6bfc3f92c5e43581833b06c318ff20cebbd9926e3ee0d673
 size 250490408

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2faf34cac979c57dfb55da136bfa774c54eaef839c48e6205e326aa7111a8154
+oid sha256:e83c83741841127291068ca3f8911471f56d6b38a3a1f40a3c482d2c41d2eeca
 size 255266042

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c659953fa2749100d286c777ca42cee4acfebcb66827f7bc777ef8c79c6ffa46
+oid sha256:3f80645c9c28658b6a91789122fec4c641bc39c0d4f1a7e56cb96853b18e402c
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6165eeddacf3a11e1b3e53c4e5290a59148da44d6a02a50c118da0899808e516
+oid sha256:e1d9325eceea92ca65820843d153b2cb31175794a5ccd0a723b229ca76e45f58
 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": 25.0,
+  "epoch": 29.166666666666668,
   "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": 144.976,
       "eval_steps_per_second": 2.318,
       "step": 300
+    },
+    {
+      "epoch": 25.833333333333332,
+      "grad_norm": 3.84375,
+      "learning_rate": 0.00010275543423681621,
+      "loss": 2.7693,
+      "step": 310
+    },
+    {
+      "epoch": 26.666666666666668,
+      "grad_norm": 4.25,
+      "learning_rate": 9.724456576318381e-05,
+      "loss": 2.7404,
+      "step": 320
+    },
+    {
+      "epoch": 27.5,
+      "grad_norm": 3.28125,
+      "learning_rate": 9.174206545276677e-05,
+      "loss": 2.7013,
+      "step": 330
+    },
+    {
+      "epoch": 28.333333333333332,
+      "grad_norm": 3.734375,
+      "learning_rate": 8.626464421815919e-05,
+      "loss": 2.6912,
+      "step": 340
+    },
+    {
+      "epoch": 29.166666666666668,
+      "grad_norm": 3.546875,
+      "learning_rate": 8.082893680762619e-05,
+      "loss": 2.6459,
+      "step": 350
+    },
+    {
+      "epoch": 29.166666666666668,
+      "eval_loss": 3.04976749420166,
+      "eval_runtime": 10.3469,
+      "eval_samples_per_second": 145.068,
+      "eval_steps_per_second": 2.32,
+      "step": 350
     }
   ],
   "logging_steps": 10,
@@ -292,7 +335,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.9436991670124544e+16,
+  "total_flos": 2.267910316543181e+16,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null