Training in progress, step 90, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63427fd5e1e8726c8901efda122025325481be1aef9249006d2594913a7b4867
+oid sha256:5e3c5278fb93831e6bf74c431d81bf4ea01752541c696075d34a1165da383dbb
 size 91951912

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a85384343dd055a0ca7b74b761fb9eca460ddf5a4d9f5621cd9eebd7543d1928
+oid sha256:34374501cdc75b6a78903d703ba1150ef06555d806a06817abb264d3fac63981
 size 183993547

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:363c5df1543d2c82b2f13164f35bdd0367ceb32e7fa1b2f67c19df073a08b17b
+oid sha256:17cd930da9783ca70bad4b9cdeee6a06c0acea8f34645a333c93341f487f66a3
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3fddde861c6a563bc3ccdf76b251044566d233012636c26a0468dcb4b6349c6
+oid sha256:a9977a4160882229fde0bd42c2a2265abbb62ba45710b05142675c1018b0ba78
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.008,
+  "epoch": 0.009,
   "eval_steps": 10,
-  "global_step": 80,
+  "global_step": 90,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -632,6 +632,84 @@
       "eval_samples_per_second": 14.68,
       "eval_steps_per_second": 1.835,
       "step": 80
+    },
+    {
+      "epoch": 0.0081,
+      "grad_norm": 0.10746733844280243,
+      "learning_rate": 0.0008,
+      "loss": 0.1001,
+      "step": 81
+    },
+    {
+      "epoch": 0.0082,
+      "grad_norm": 0.0835120752453804,
+      "learning_rate": 0.0008100000000000001,
+      "loss": 0.0699,
+      "step": 82
+    },
+    {
+      "epoch": 0.0083,
+      "grad_norm": 0.13253141939640045,
+      "learning_rate": 0.00082,
+      "loss": 0.0795,
+      "step": 83
+    },
+    {
+      "epoch": 0.0084,
+      "grad_norm": 0.08485159277915955,
+      "learning_rate": 0.00083,
+      "loss": 0.0697,
+      "step": 84
+    },
+    {
+      "epoch": 0.0085,
+      "grad_norm": 0.14905264973640442,
+      "learning_rate": 0.0008400000000000001,
+      "loss": 0.0928,
+      "step": 85
+    },
+    {
+      "epoch": 0.0086,
+      "grad_norm": 0.9524427652359009,
+      "learning_rate": 0.00085,
+      "loss": 0.3045,
+      "step": 86
+    },
+    {
+      "epoch": 0.0087,
+      "grad_norm": 0.5842136740684509,
+      "learning_rate": 0.0008600000000000001,
+      "loss": 0.1334,
+      "step": 87
+    },
+    {
+      "epoch": 0.0088,
+      "grad_norm": 0.11962056159973145,
+      "learning_rate": 0.00087,
+      "loss": 0.0735,
+      "step": 88
+    },
+    {
+      "epoch": 0.0089,
+      "grad_norm": 0.057546887546777725,
+      "learning_rate": 0.00088,
+      "loss": 0.0477,
+      "step": 89
+    },
+    {
+      "epoch": 0.009,
+      "grad_norm": 0.14116229116916656,
+      "learning_rate": 0.0008900000000000001,
+      "loss": 0.0651,
+      "step": 90
+    },
+    {
+      "epoch": 0.009,
+      "eval_loss": 0.013806294649839401,
+      "eval_runtime": 680.6174,
+      "eval_samples_per_second": 14.693,
+      "eval_steps_per_second": 1.837,
+      "step": 90
     }
   ],
   "logging_steps": 1,