Training in progress, step 3900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cde6f153e1e8b9a9e7c00323ae4d7db7386328f2d24b06facfc13a8ee245b3fe
+oid sha256:0391a43e44101ba1c8646a6094f6b65cec4318f22c74e9c2ae40b34185f7cc5d
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:124b7ab2647d2a34f2d76c3fe8f556de61ab2239e56a049ecc9fdd7887cdf35e
+oid sha256:09e8ffb13099b6ec8a1019bcdb942d10f9971ad077f0de806881fa51c83496d4
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cbc3f7eb6570c006a685ab90bed6095506dc3296d40e802ec891bd2b2edc3fe
+oid sha256:81e66deaa7a6347bec6d2635166d3c92ba13107fc8c837f587e530f8f9f6413f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:073260aeda648df98a231950123c1b6238009c89906d5834aa58374e8953701f
+oid sha256:17f09240eb3a2df53c686d502e0925c2a9bbb6edcd515f95977492c20f85fc70
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3104,
+  "epoch": 0.312,
   "eval_steps": 500,
-  "global_step": 3880,
+  "global_step": 3900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1365,6 +1365,13 @@
       "learning_rate": 2.793333244167681e-05,
       "loss": 3.5345,
       "step": 3880
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 29.29547119140625,
+      "learning_rate": 2.790865673705888e-05,
+      "loss": 3.4588,
+      "step": 3900
     }
   ],
   "logging_steps": 20,
@@ -1372,7 +1379,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 9159181149831168.0,
+  "total_flos": 9202648983994368.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null