Training in progress, step 63, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21a2ed8bed0ddab03d5a17dafbeb7e50a831be8f7ac2a397524311182c9fcf80
+oid sha256:6025d2368312752b86b7edf0c0bc416c221cc07f2a3f3246f0089144bc31ee01
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f0f9901a4aba35c49ab4df7668ec2b5de3dc39624803f58e5c67bc4e07b9f52
+oid sha256:e6f655d8ffc9cd307536c7c01014c1a6d177aaff88710c2cdb1a2de1ab3673a0
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd6d473887d334bf3b11498ce01072f912b255c60c14b4797c2dbfc29a352e36
+oid sha256:69363b571608ea891a243316f5833df4d3c3af272068a043b9b978810851ad3a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2011b1e019073e4bafc29de9703ff0a6e7c1252c3a53d804807bd1c99d390d1c
+oid sha256:e53b95eff99f2334cbf7ed4c962db83cb42e931305982518e928382563b5670d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2026266416510319,
+  "epoch": 0.23639774859287055,
   "eval_steps": 9,
-  "global_step": 54,
+  "global_step": 63,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -189,6 +189,35 @@
       "eval_samples_per_second": 13.672,
       "eval_steps_per_second": 3.464,
       "step": 54
+    },
+    {
+      "epoch": 0.21388367729831145,
+      "grad_norm": 0.01664595864713192,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 0.0006,
+      "step": 57
+    },
+    {
+      "epoch": 0.225140712945591,
+      "grad_norm": 2.271406888961792,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.0372,
+      "step": 60
+    },
+    {
+      "epoch": 0.23639774859287055,
+      "grad_norm": 0.012259761802852154,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 0.021,
+      "step": 63
+    },
+    {
+      "epoch": 0.23639774859287055,
+      "eval_loss": 0.005822421051561832,
+      "eval_runtime": 16.4688,
+      "eval_samples_per_second": 13.662,
+      "eval_steps_per_second": 3.461,
+      "step": 63
     }
   ],
   "logging_steps": 3,
@@ -208,7 +237,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.839099450425344e+16,
+  "total_flos": 4.478949358829568e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null