Training in progress, step 920, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bacbcdeb772271ae4a73b553452403dd574bd8d136434ea8e8a57d0663616033
+oid sha256:824b0482f65c54d780bf8cab1640646068f4412a35e93bf84312042275c949aa
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bb997ee1b9cc31b655c80659a8be14291f7c87e0520c3fe55461fe9ea80dc5a
+oid sha256:fd7608b89dafbdc3e9ff64304083584d3644129f923c4a985f1eb00d503b9fd9
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40fb52d754072900f939e68c95258ed986e02ba250a7a6a809e0b910ea21aa4b
+oid sha256:a88d647ecb4240893f5936ba5eb3da134925ec105812fc12c4afbef4944427f9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26e4e7bb751929813cc507d4c008baeb62df515276167a2e28f789b23a39f84f
+oid sha256:799790dec230733f2507fb25ac7c0f3b89a16d8c9935acbdd39b641fa24a7e12
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.072,
+  "epoch": 0.0736,
   "eval_steps": 500,
-  "global_step": 900,
+  "global_step": 920,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -322,6 +322,13 @@
       "learning_rate": 2.998230238919386e-05,
       "loss": 3.7376,
       "step": 900
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 27.453275680541992,
+      "learning_rate": 2.9979864597363846e-05,
+      "loss": 3.6716,
+      "step": 920
     }
   ],
   "logging_steps": 20,
@@ -329,7 +336,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 2126840118214656.0,
+  "total_flos": 2178771877822464.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null