Training in progress, step 2780, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b7c4a44abf8634f7abd4ae2e7c69c9985e580503513a18830a2ecd874d0f563
+oid sha256:654b23694cdd1bbec4f90862155f3f41c2a6bcac9229cb226a66d80cc205f4cc
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6523b809018c23a175a6391f7281cb9e9f51b92a78e512668164068571daab52
+oid sha256:e2fdce7da28ed66b3d91cfa2a1cbe53544b2858c9aa4b494826630ef96e4b87c
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d02bb0ca8829dd2c6092c231d8f86f0365111ccb21a1e6b4322c7eda5086789
+oid sha256:d27a260316eae40f12eb26cf979926c13542623ae9f28e7854a86a259b8f86ac
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d857a77763b85adde3e5e30fb04f1ce5b7dbf57906196936546a9f424267aa89
+oid sha256:6154d037b631b5f05d1997c63d1a8dc99cf7eb96d3d6cf27edbd3ad94f018941
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2208,
+  "epoch": 0.2224,
   "eval_steps": 500,
-  "global_step": 2760,
+  "global_step": 2780,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -973,6 +973,13 @@
       "learning_rate": 2.909169326286807e-05,
       "loss": 3.4967,
       "step": 2760
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 41.78467559814453,
+      "learning_rate": 2.9074970738873054e-05,
+      "loss": 3.6409,
+      "step": 2780
     }
   ],
   "logging_steps": 20,
@@ -980,7 +987,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 6537004557631488.0,
+  "total_flos": 6577585471488000.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null