Training in progress, step 250, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c36e0e6e72d331231c75519120e36a9242a8bff07537a0f65827a336f1b79a44
+oid sha256:b48563b44d44362320f067d34ff92f47e2456bde4f2317ee93b23dabf1b45729
 size 2066752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99f20a54dee8d027bcc9bbaea42ff161e8cbba806bb3f35869be2a2f744d29fc
+oid sha256:cb5dc22ec383dbcee021a17c4623070dde01a829463bd7b6d6d98d76a1a52d83
 size 2162798

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b9a2678740824fb589a72819ef8a2601a1af7909330828a265812e5b5ff9c95
+oid sha256:a04a9f6de7412b2745ad1e05df32de31ca01887f6c3263f961d3bee484ab3809
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db973c8a6e8032795aca2e0edfd5e46b92aea774c79981d12eef1bcb25c3d7d4
+oid sha256:e80f5d18253859eb582d273afcfab47d6dbe284f74a1acab6df29c9bd8e3ef5d
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cd11d413bc67bf01de9a1a006e9e7655be307353028b25f5b3c299e5b6b7a44
+oid sha256:748ed266e9432323e41e747f49e84d108918da883711ff6e01c8135af1c286fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 15.384615384615385,
+  "epoch": 19.23076923076923,
   "eval_steps": 50,
-  "global_step": 200,
+  "global_step": 250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,49 @@
       "eval_samples_per_second": 284.283,
       "eval_steps_per_second": 4.545,
       "step": 200
+    },
+    {
+      "epoch": 16.153846153846153,
+      "grad_norm": 0.3828125,
+      "learning_rate": 0.00015469481581224272,
+      "loss": 9.4734,
+      "step": 210
+    },
+    {
+      "epoch": 16.923076923076923,
+      "grad_norm": 0.388671875,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 9.4381,
+      "step": 220
+    },
+    {
+      "epoch": 17.692307692307693,
+      "grad_norm": 0.39453125,
+      "learning_rate": 0.00014515333583108896,
+      "loss": 9.4021,
+      "step": 230
+    },
+    {
+      "epoch": 18.46153846153846,
+      "grad_norm": 0.396484375,
+      "learning_rate": 0.00014016954246529696,
+      "loss": 9.3725,
+      "step": 240
+    },
+    {
+      "epoch": 19.23076923076923,
+      "grad_norm": 0.396484375,
+      "learning_rate": 0.00013506375551927547,
+      "loss": 9.3407,
+      "step": 250
+    },
+    {
+      "epoch": 19.23076923076923,
+      "eval_loss": 9.341134071350098,
+      "eval_runtime": 5.9586,
+      "eval_samples_per_second": 251.904,
+      "eval_steps_per_second": 4.028,
+      "step": 250
     }
   ],
   "logging_steps": 10,
@@ -206,7 +249,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 81831709900800.0,
+  "total_flos": 102289637376000.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null