Training in progress, step 9000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac1a75e495e37659f935a94a153e5ae964ac453c26fb6a9e6d16dca433447a46
+oid sha256:a965268f22c4e79d69dbf95ac68df18131ac4a28a88a5d81432e568fd272e719
 size 1783055976

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c30fdbb96dddd647ac7cab10b09e0ee2785b645bae4fc61cc48fe5171deae209
+oid sha256:5b417a00b6bce03f65479ff59686f2d226987f315fc5c6151693c6b7ec367ec9
 size 3566173562

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9213080fe2b45399b87036ca9ff9164533abe6b368e5c828136ee184486749d4
+oid sha256:86a2aa7bca84d2b8e7dd4e04a286714ba9169af11c46c739950a52df4c45259f
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68f6c298533d8c912a29bc1b5e945c92e9b2f851b00f21834ca034f7df9e34ae
+oid sha256:cb8278e710e71ee2631a6ab6373f5d2bf3048e7d5a86c6ca348c577a5e8dd794
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3965fdcf65adda4a516b1c5cd32d581e539d552e45f86bb9fe1a08df9bbf9fad
+oid sha256:695726e815b6f66e1dd703432b138d1f45b6d5a74f2a6894ef9031edc67f71e7
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.07604673295406889,
+  "epoch": 0.08052007018666119,
   "eval_steps": 500,
-  "global_step": 8500,
+  "global_step": 9000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1334,6 +1334,84 @@
       "eval_samples_per_second": 39.877,
       "eval_steps_per_second": 4.988,
       "step": 8500
+    },
+    {
+      "epoch": 0.07649406667732812,
+      "grad_norm": 0.5514459013938904,
+      "learning_rate": 4.249005964214712e-05,
+      "loss": 0.2999,
+      "step": 8550
+    },
+    {
+      "epoch": 0.07694140040058735,
+      "grad_norm": 0.4008141756057739,
+      "learning_rate": 4.2738568588469184e-05,
+      "loss": 0.2995,
+      "step": 8600
+    },
+    {
+      "epoch": 0.07738873412384657,
+      "grad_norm": 0.5259721279144287,
+      "learning_rate": 4.298707753479125e-05,
+      "loss": 0.3023,
+      "step": 8650
+    },
+    {
+      "epoch": 0.07783606784710581,
+      "grad_norm": 0.45233720541000366,
+      "learning_rate": 4.323558648111332e-05,
+      "loss": 0.2988,
+      "step": 8700
+    },
+    {
+      "epoch": 0.07828340157036504,
+      "grad_norm": 0.5091809034347534,
+      "learning_rate": 4.348409542743539e-05,
+      "loss": 0.2904,
+      "step": 8750
+    },
+    {
+      "epoch": 0.07873073529362426,
+      "grad_norm": 0.4471395015716553,
+      "learning_rate": 4.3732604373757455e-05,
+      "loss": 0.2964,
+      "step": 8800
+    },
+    {
+      "epoch": 0.0791780690168835,
+      "grad_norm": 0.42044690251350403,
+      "learning_rate": 4.398111332007953e-05,
+      "loss": 0.2967,
+      "step": 8850
+    },
+    {
+      "epoch": 0.07962540274014272,
+      "grad_norm": 0.5424165725708008,
+      "learning_rate": 4.4229622266401594e-05,
+      "loss": 0.2881,
+      "step": 8900
+    },
+    {
+      "epoch": 0.08007273646340195,
+      "grad_norm": 0.4515838325023651,
+      "learning_rate": 4.447813121272366e-05,
+      "loss": 0.293,
+      "step": 8950
+    },
+    {
+      "epoch": 0.08052007018666119,
+      "grad_norm": 0.46129104495048523,
+      "learning_rate": 4.472664015904573e-05,
+      "loss": 0.2947,
+      "step": 9000
+    },
+    {
+      "epoch": 0.08052007018666119,
+      "eval_loss": 0.2950306236743927,
+      "eval_runtime": 225.9158,
+      "eval_samples_per_second": 39.984,
+      "eval_steps_per_second": 5.002,
+      "step": 9000
     }
   ],
   "logging_steps": 50,
@@ -1353,7 +1431,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0941622124544e+17,
+  "total_flos": 1.31299465494528e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null