Training in progress, step 80, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35a42b55d3701e5a12697fd5924d974cea7f163c0cb91d6f9ac4e4cb8ff03cf8
+oid sha256:63427fd5e1e8726c8901efda122025325481be1aef9249006d2594913a7b4867
 size 91951912

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbddab535ba95148e0089b9f3f4b8a1f5977ce21e43febf1c71c5a4c705de66c
+oid sha256:a85384343dd055a0ca7b74b761fb9eca460ddf5a4d9f5621cd9eebd7543d1928
 size 183993547

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdc37bbd2e979f041dfbbb004a5c74bab6cdda159cb18116df728588515a9ef6
+oid sha256:363c5df1543d2c82b2f13164f35bdd0367ceb32e7fa1b2f67c19df073a08b17b
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27b816657813df7e52eea7ed78398d45823427f2a8ddca6aba5083c28583e963
+oid sha256:c3fddde861c6a563bc3ccdf76b251044566d233012636c26a0468dcb4b6349c6
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.007,
+  "epoch": 0.008,
   "eval_steps": 10,
-  "global_step": 70,
+  "global_step": 80,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -554,6 +554,84 @@
       "eval_samples_per_second": 14.661,
       "eval_steps_per_second": 1.833,
       "step": 70
+    },
+    {
+      "epoch": 0.0071,
+      "grad_norm": 0.550254762172699,
+      "learning_rate": 0.0007,
+      "loss": 0.5598,
+      "step": 71
+    },
+    {
+      "epoch": 0.0072,
+      "grad_norm": 0.21443326771259308,
+      "learning_rate": 0.00071,
+      "loss": 0.23,
+      "step": 72
+    },
+    {
+      "epoch": 0.0073,
+      "grad_norm": 0.25100332498550415,
+      "learning_rate": 0.0007199999999999999,
+      "loss": 0.2287,
+      "step": 73
+    },
+    {
+      "epoch": 0.0074,
+      "grad_norm": 0.8701838850975037,
+      "learning_rate": 0.0007300000000000001,
+      "loss": 0.8359,
+      "step": 74
+    },
+    {
+      "epoch": 0.0075,
+      "grad_norm": 0.19172491133213043,
+      "learning_rate": 0.00074,
+      "loss": 0.1903,
+      "step": 75
+    },
+    {
+      "epoch": 0.0076,
+      "grad_norm": 0.15641027688980103,
+      "learning_rate": 0.00075,
+      "loss": 0.13,
+      "step": 76
+    },
+    {
+      "epoch": 0.0077,
+      "grad_norm": 0.1556449830532074,
+      "learning_rate": 0.00076,
+      "loss": 0.1248,
+      "step": 77
+    },
+    {
+      "epoch": 0.0078,
+      "grad_norm": 0.2690158486366272,
+      "learning_rate": 0.00077,
+      "loss": 0.1378,
+      "step": 78
+    },
+    {
+      "epoch": 0.0079,
+      "grad_norm": 0.17920906841754913,
+      "learning_rate": 0.0007800000000000001,
+      "loss": 0.1314,
+      "step": 79
+    },
+    {
+      "epoch": 0.008,
+      "grad_norm": 0.13513772189617157,
+      "learning_rate": 0.0007899999999999999,
+      "loss": 0.0999,
+      "step": 80
+    },
+    {
+      "epoch": 0.008,
+      "eval_loss": 0.019889511168003082,
+      "eval_runtime": 681.178,
+      "eval_samples_per_second": 14.68,
+      "eval_steps_per_second": 1.835,
+      "step": 80
     }
   ],
   "logging_steps": 1,