Training in progress, step 210, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fccb9d19391a43ae36da2a29dca1396279a90010220baf3fdc58dd3a829f12c
+oid sha256:7d259edcf51a6e65a5e5aa8f076d5bc4bf480fc4b4c59350991263774074d7ea
 size 67662840

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27344c3587987f033a2e10256a7429eafce2d23bd1d8359720449b41078b595b
+oid sha256:b0503c8ba76bfe0abdcb3e8a6104759013bd2d60c838b4625f0a1ddcf7615226
 size 34607610

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c4869346972db0176eb12ec757dcc0880dcf0f71294066b4e62ba14aee601ed
+oid sha256:2bfc5fa47af4dae874a1be827d0f45774971f451a821e11602842d4ee93aaa71
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:194047adc90239b1536a6d8862bfb9a2319ff9742b72adc68dd878597757d341
+oid sha256:29055dd59dc6fec528a1dd0a8f1388fe1bcd85af7ce5330f9713cff07d4913e7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 6.456692913385827,
+  "epoch": 6.6141732283464565,
   "eval_steps": 8,
-  "global_step": 205,
+  "global_step": 210,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1650,6 +1650,49 @@
       "learning_rate": 4.5379898746037804e-05,
       "loss": 0.8624,
       "step": 205
+    },
+    {
+      "epoch": 6.488188976377953,
+      "grad_norm": 1.210954189300537,
+      "learning_rate": 4.529436096395156e-05,
+      "loss": 0.9547,
+      "step": 206
+    },
+    {
+      "epoch": 6.519685039370079,
+      "grad_norm": 1.2978620529174805,
+      "learning_rate": 4.520812077077604e-05,
+      "loss": 0.8868,
+      "step": 207
+    },
+    {
+      "epoch": 6.551181102362205,
+      "grad_norm": 1.081527590751648,
+      "learning_rate": 4.5121181151383143e-05,
+      "loss": 0.7841,
+      "step": 208
+    },
+    {
+      "epoch": 6.551181102362205,
+      "eval_loss": 1.2477138042449951,
+      "eval_runtime": 3.8991,
+      "eval_samples_per_second": 25.647,
+      "eval_steps_per_second": 1.795,
+      "step": 208
+    },
+    {
+      "epoch": 6.582677165354331,
+      "grad_norm": 1.1496070623397827,
+      "learning_rate": 4.503354511485273e-05,
+      "loss": 0.9487,
+      "step": 209
+    },
+    {
+      "epoch": 6.6141732283464565,
+      "grad_norm": 1.188530683517456,
+      "learning_rate": 4.494521569436845e-05,
+      "loss": 0.9439,
+      "step": 210
     }
   ],
   "logging_steps": 1,
@@ -1669,7 +1712,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.3305746833408e+16,
+  "total_flos": 3.4155451121664e+16,
   "train_batch_size": 15,
   "trial_name": null,
   "trial_params": null