Training in progress, step 80, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61e5c0f35b71c9983b3e424393dd63559abb6777f17c007d00400502f5c6d723
+oid sha256:5593b252d028f88e05bf30892eb4a8c80af2011995cb9314cb7caca9bd19f598
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe843929a1a7ffab1ada0c40c5121ac85239b10feec1bab0b4a244b642b35afe
+oid sha256:806ed047d7880675490e96052a591aeba3453056c5e482dca7fa76f91a3b9e7d
 size 49846260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9985ffa062c456961c906611c6eefe1ec3f2ec72fc76fa78844769d2f605ee6
+oid sha256:57209a64907c7bb6c51058259e330f3fccde6c159d24fc13e54a5593f82bf526
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6dab1ac154b81ac30a29341f70a9f4ad70acdf8ad002b67de5d1dcf11c0a4176
+oid sha256:05fb2eb621a35698b1b27ac2b241995d61d21940c991c54ed191d76781b55e85
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.09705596894208994,
+  "epoch": 0.1035263668715626,
   "eval_steps": 386,
-  "global_step": 75,
+  "global_step": 80,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -540,6 +540,41 @@
       "learning_rate": 9.998937682243215e-05,
       "loss": 1.0456,
       "step": 75
+    },
+    {
+      "epoch": 0.09835004852798447,
+      "grad_norm": 1.3232612609863281,
+      "learning_rate": 9.998851000434448e-05,
+      "loss": 0.9994,
+      "step": 76
+    },
+    {
+      "epoch": 0.099644128113879,
+      "grad_norm": 1.2017115354537964,
+      "learning_rate": 9.998760919869883e-05,
+      "loss": 1.2664,
+      "step": 77
+    },
+    {
+      "epoch": 0.10093820769977353,
+      "grad_norm": 1.0694175958633423,
+      "learning_rate": 9.998667440610765e-05,
+      "loss": 0.9483,
+      "step": 78
+    },
+    {
+      "epoch": 0.10223228728566806,
+      "grad_norm": 0.9963059425354004,
+      "learning_rate": 9.998570562720654e-05,
+      "loss": 0.9577,
+      "step": 79
+    },
+    {
+      "epoch": 0.1035263668715626,
+      "grad_norm": 0.8873535394668579,
+      "learning_rate": 9.998470286265416e-05,
+      "loss": 0.8498,
+      "step": 80
     }
   ],
   "logging_steps": 1,
@@ -559,7 +594,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.38452878770176e+16,
+  "total_flos": 8.943497373548544e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null