Training in progress, step 45, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:753c7f048d3c17a8dff05f7e48fa6cf023fc614649bb13ef4db1a60157f75a09
+oid sha256:bbef157b9600fdc30cd09681e635c3596d9d9f3a832f0d58792888176093d6e7
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9012b11cde3a2f0c54dbc6f706596bd3a5f30e4c957cf2683a03dee748e9f767
+oid sha256:16278e58faf54743e51c2cb86c8c7a4cef307e814c0ff1c955065184c7b3ffbf
 size 49846260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6c5ab014d4aef79b98314290c49544dc6945723046a24993974bca5a70c4fbb
+oid sha256:1d0fa37673dbc0bf8164a593d75abf6e8c224c2ea3193e0f86621fb2aa8c6ed6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b1e5be422da84e599b3b273b39d45d7ca20a6f0b0460857ee0c0fe6a229a2c9
+oid sha256:cd1931e4016bf28b07346e79413c71e240f12f43909f7431de607b5c05407707
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0517631834357813,
+  "epoch": 0.058233581365253966,
   "eval_steps": 386,
-  "global_step": 40,
+  "global_step": 45,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -295,6 +295,41 @@
       "learning_rate": 8e-05,
       "loss": 1.2779,
       "step": 40
+    },
+    {
+      "epoch": 0.053057263021675835,
+      "grad_norm": 1.254847526550293,
+      "learning_rate": 8.2e-05,
+      "loss": 1.0898,
+      "step": 41
+    },
+    {
+      "epoch": 0.054351342607570366,
+      "grad_norm": 1.1771515607833862,
+      "learning_rate": 8.4e-05,
+      "loss": 1.1827,
+      "step": 42
+    },
+    {
+      "epoch": 0.0556454221934649,
+      "grad_norm": 1.1400648355484009,
+      "learning_rate": 8.6e-05,
+      "loss": 1.1066,
+      "step": 43
+    },
+    {
+      "epoch": 0.05693950177935943,
+      "grad_norm": 1.2047138214111328,
+      "learning_rate": 8.800000000000001e-05,
+      "loss": 0.8974,
+      "step": 44
+    },
+    {
+      "epoch": 0.058233581365253966,
+      "grad_norm": 1.1269346475601196,
+      "learning_rate": 9e-05,
+      "loss": 1.0146,
+      "step": 45
     }
   ],
   "logging_steps": 1,
@@ -314,7 +349,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.471748686774272e+16,
+  "total_flos": 5.030717272621056e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null