Training in progress, step 900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:122f732830a82f1a7a3a7425537e862e7ee1d697cd8187d0044646345b434143
+oid sha256:bacbcdeb772271ae4a73b553452403dd574bd8d136434ea8e8a57d0663616033
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa28364534d96be46cefdbe1b76cf7a40940e1cf04c4f5a6cf3ccbb915f922bc
+oid sha256:7bb997ee1b9cc31b655c80659a8be14291f7c87e0520c3fe55461fe9ea80dc5a
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dea0e7f5f0c188c2ee6e729843388c15e47a905456029356105d7ca29f2d0fef
+oid sha256:40fb52d754072900f939e68c95258ed986e02ba250a7a6a809e0b910ea21aa4b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52aa474262a07e7da5493acb71323699d3a95e420cf1220730538dffbf9e1ae4
+oid sha256:26e4e7bb751929813cc507d4c008baeb62df515276167a2e28f789b23a39f84f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0704,
+  "epoch": 0.072,
   "eval_steps": 500,
-  "global_step": 880,
+  "global_step": 900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -315,6 +315,13 @@
       "learning_rate": 2.9984583023761318e-05,
       "loss": 3.7271,
       "step": 880
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 26.61457061767578,
+      "learning_rate": 2.998230238919386e-05,
+      "loss": 3.7376,
+      "step": 900
     }
   ],
   "logging_steps": 20,
@@ -322,7 +329,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 2079501186367488.0,
+  "total_flos": 2126840118214656.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null