Training in progress, step 2760, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d9e8b32b966f871c511b5657fa29716b505e3b46707edada57780def8a3a4f0
+oid sha256:1b7c4a44abf8634f7abd4ae2e7c69c9985e580503513a18830a2ecd874d0f563
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09d1dd512e5173901c2f4b3e632283257f9e9c5e3f7e6ab6ae19723b4371d0b6
+oid sha256:6523b809018c23a175a6391f7281cb9e9f51b92a78e512668164068571daab52
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91283a9e0978c1c4026d0596abe9afca642afabfe3852b23f40302b2b4a58b48
+oid sha256:4d02bb0ca8829dd2c6092c231d8f86f0365111ccb21a1e6b4322c7eda5086789
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a07583ff04916149d2b98a04a5a3645539e81ed096b0a41ed14e70c156517bb
+oid sha256:d857a77763b85adde3e5e30fb04f1ce5b7dbf57906196936546a9f424267aa89
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2192,
+  "epoch": 0.2208,
   "eval_steps": 500,
-  "global_step": 2740,
+  "global_step": 2760,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -966,6 +966,13 @@
       "learning_rate": 2.9108267971668828e-05,
       "loss": 3.5082,
       "step": 2740
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 26.25998878479004,
+      "learning_rate": 2.909169326286807e-05,
+      "loss": 3.4967,
+      "step": 2760
     }
   ],
   "logging_steps": 20,
@@ -973,7 +980,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 6492126069227520.0,
+  "total_flos": 6537004557631488.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null