Training in progress, step 72, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80b2341746d451e80bbdaa38078c698851da6d535641174f8590c6ce350bc0b9
+oid sha256:0dd83e8a68ff0b516522fae1b1dfdddc57ab17f6a67f83b6713c5d3b4020df2f
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6193aa356518d7410816906e8c32211cdf79826f330a7a3197988369a670b5b2
+oid sha256:f995c8da7cf862606d0b3fab16e8b9d5bbe66b1aab0a12da1e7bbbbf4b6fd747
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49644ad8f5452e53758ca52013eb3650a3941bcec6083d72c46c935a677f7d88
+oid sha256:455977057132821379da92f1a77f9b1f540991d9dd7c684ba956aca72c970f71
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:922634a168fad3088c2a461ec82359f2941891b1472f492b835996e27c3cba9d
+oid sha256:d899e046e5eb8fee9b81979db8db7b88d6dc92f30a13d049b906f3a3be1dfc0f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.046875,
+  "epoch": 0.05357142857142857,
   "eval_steps": 9,
-  "global_step": 63,
+  "global_step": 72,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -218,6 +218,35 @@
       "eval_samples_per_second": 13.98,
       "eval_steps_per_second": 1.747,
       "step": 63
+    },
+    {
+      "epoch": 0.049107142857142856,
+      "grad_norm": 6.4269185066223145,
+      "learning_rate": 1.56348351646022e-05,
+      "loss": 3.9744,
+      "step": 66
+    },
+    {
+      "epoch": 0.05133928571428571,
+      "grad_norm": 5.94874382019043,
+      "learning_rate": 1.3263210930352737e-05,
+      "loss": 3.9959,
+      "step": 69
+    },
+    {
+      "epoch": 0.05357142857142857,
+      "grad_norm": 5.269709587097168,
+      "learning_rate": 1.1020177413231334e-05,
+      "loss": 4.0065,
+      "step": 72
+    },
+    {
+      "epoch": 0.05357142857142857,
+      "eval_loss": 4.0851731300354,
+      "eval_runtime": 161.9017,
+      "eval_samples_per_second": 13.984,
+      "eval_steps_per_second": 1.748,
+      "step": 72
     }
   ],
   "logging_steps": 3,
@@ -237,7 +266,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.347779772861645e+16,
+  "total_flos": 1.0683176883270451e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null