Training in progress, epoch 10, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff33ba1981fd23c9a70194ad44249bad6efd85e3f45f87477a5679eb64fba9d6
+oid sha256:83b04a37d9211fc9f3a2f5ee765c372b7399c2c32da2986ce47eb5cff823e7b5
 size 540033204

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce259efefbd0a669e092d069f8b7d0abeebece2ba65572da40dbc9cb4f2c7f00
+oid sha256:b2ae383c5dcaf76dde1c874222526aed13cb1fc56743a75701100cefa130a1cf
 size 1080178938

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b884a31436e5a926c6a4b2ab322392a191669d607ca1d807ba3a04c0729344f
+oid sha256:be4437ab9357b241b2f020ec944b34548e5dfaaa7a705c7a5eac18d0f2b84fc3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c1a5a0490d673c1b146e0e96e5387b572aaad76740cc2aa549f781d311acc2b
+oid sha256:ee470bc0e61484a1d4859a97cb99ce2ce1081559b51f977be74512e7900e4f6c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.0,
+  "epoch": 10.0,
   "eval_steps": 500,
-  "global_step": 72,
+  "global_step": 80,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -583,6 +583,70 @@
       "eval_samples_per_second": 32.211,
       "eval_steps_per_second": 0.33,
       "step": 72
+    },
+    {
+      "epoch": 9.125,
+      "grad_norm": 47.713768005371094,
+      "learning_rate": 1.146356783919598e-07,
+      "loss": 3.6657,
+      "step": 73
+    },
+    {
+      "epoch": 9.25,
+      "grad_norm": 48.04665756225586,
+      "learning_rate": 1.1620603015075378e-07,
+      "loss": 3.635,
+      "step": 74
+    },
+    {
+      "epoch": 9.375,
+      "grad_norm": 47.147972106933594,
+      "learning_rate": 1.1777638190954775e-07,
+      "loss": 3.6149,
+      "step": 75
+    },
+    {
+      "epoch": 9.5,
+      "grad_norm": 47.14889144897461,
+      "learning_rate": 1.193467336683417e-07,
+      "loss": 3.5891,
+      "step": 76
+    },
+    {
+      "epoch": 9.625,
+      "grad_norm": 47.27253723144531,
+      "learning_rate": 1.209170854271357e-07,
+      "loss": 3.56,
+      "step": 77
+    },
+    {
+      "epoch": 9.75,
+      "grad_norm": 47.30030822753906,
+      "learning_rate": 1.2248743718592966e-07,
+      "loss": 3.554,
+      "step": 78
+    },
+    {
+      "epoch": 9.875,
+      "grad_norm": 46.53535461425781,
+      "learning_rate": 1.2405778894472362e-07,
+      "loss": 3.5081,
+      "step": 79
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 46.524356842041016,
+      "learning_rate": 1.256281407035176e-07,
+      "loss": 3.4906,
+      "step": 80
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 3.130697011947632,
+      "eval_runtime": 44.7299,
+      "eval_samples_per_second": 30.539,
+      "eval_steps_per_second": 0.313,
+      "step": 80
     }
   ],
   "logging_steps": 1,
@@ -597,7 +661,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }