Training in progress, step 40, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbc29a0fbddbc8f2aee33509d8b46ffb148b09e99f87205a9339cd29be7a4c9f
+oid sha256:6ff04ffbfa8bc5bb3e988c8bb45003fcadd064e85f411987ddd44c15d8d57974
 size 250490408

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:011384e0bf4163d9eaa823c6126a17099909c178bcbae1f784e3255e34352ad7
+oid sha256:d243f90d71e2db4783c193c779aa1f22097b9f05a55dcf25053864cf43dd5dfa
 size 255265850

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7f1384a95c7886d45389c40a6a90ac8328081e721eba74d7efd9c04824bd482
+oid sha256:6d0bc5c92e4fdea01d3fa32e0069da72f87be35dfa69240211a2193fb469268f
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7c49e91ee5c51b4cb45c0ea51ec7a52a5fe9832d924e46824fac4bed28529c7
+oid sha256:fed34d3582eb7589bf4ae83ba37735e55c58c1dcea5c7b347cc4732a41c1fa84
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3d7496cd5cad5fcd343f51f06f864ca525a833da3ba71e9c4d90915510423ac
+oid sha256:572996e9dc190ff3f3a6efdf58de929f593fa2dd2f97d74fed7646828651b17f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.6666666666666665,
+  "epoch": 3.3333333333333335,
   "eval_steps": 40,
-  "global_step": 20,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -29,6 +29,28 @@
       "learning_rate": 0.00013333333333333334,
       "loss": 5.8022,
       "step": 20
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 4.03125,
+      "learning_rate": 0.0002,
+      "loss": 5.51,
+      "step": 30
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 4.3125,
+      "learning_rate": 0.00019984815164333163,
+      "loss": 5.3024,
+      "step": 40
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "eval_loss": 3.1405746936798096,
+      "eval_runtime": 10.6366,
+      "eval_samples_per_second": 141.117,
+      "eval_steps_per_second": 2.256,
+      "step": 40
     }
   ],
   "logging_steps": 10,
@@ -48,7 +70,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1311685964988416.0,
+  "total_flos": 2598287911682048.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null