Training in progress, step 40, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c06d3ba466680d20e83dca1f72ae896e45012b2aac10f1213573e33e369131a
+oid sha256:4004324ae6a287b56f6750e0088510f56f4e3770c777e917f2b7d91578c5b194
 size 847599616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9f5c15366758b9c7691ee7b8a10e03f333fe2133f38def1a5ebad01ed824459
+oid sha256:eb823174ab249b1842d4e1162abd6e67ae85179a680cff7991e0b160459185c1
 size 350603

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d93ec8d96aaa0c43a5a884ca6c90a318c00f4af0168b05a46c3f804d3a01bf7d
+oid sha256:1eb579b6634a965331bf4e2fb7490cfab58bd743a2aa0822c6275d43249a9fe6
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad4a07c066075e0a1b5d9477b0d2f4d6bab07235ad5efe05720caa179d7171b5
+oid sha256:889f6fc92910dc1617d7e2b8e49ec9358ef58d2162623ab1d55db477fded32fc
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1,
+  "epoch": 0.2,
   "eval_steps": 20,
-  "global_step": 20,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -45,6 +45,43 @@
       "eval_samples_per_second": 10.797,
       "eval_steps_per_second": 2.699,
       "step": 20
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 0.204095259308815,
+      "learning_rate": 3.9466531944960116e-06,
+      "loss": 22.034034729003906,
+      "step": 25
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.19144363701343536,
+      "learning_rate": 3.902113032590307e-06,
+      "loss": 22.034739685058593,
+      "step": 30
+    },
+    {
+      "epoch": 0.175,
+      "grad_norm": 0.20849967002868652,
+      "learning_rate": 3.844579509954769e-06,
+      "loss": 22.041725158691406,
+      "step": 35
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.1984155923128128,
+      "learning_rate": 3.7744456388872234e-06,
+      "loss": 22.034831237792968,
+      "step": 40
+    },
+    {
+      "epoch": 0.2,
+      "eval_accuracy": 2.0024420024420023e-05,
+      "eval_loss": 11.019495964050293,
+      "eval_runtime": 92.1989,
+      "eval_samples_per_second": 10.846,
+      "eval_steps_per_second": 2.712,
+      "step": 40
     }
   ],
   "logging_steps": 5,