Training in progress, step 6840, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:720b003068dffa8262fc19d67635315f97ac650b263fd177d92adc68b5e84fe8
+oid sha256:518c66ebd8ad215b6e10e1e9f964e45894e80619dac9fca6659b4f3ddeb3b3fd
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:370ab4cbab2424ee9196b0433c81cdf1630c4c010b17101af78d131d7e230efe
+oid sha256:c06d2f34d5afc5a2972610b94f622e8929acb7496b3920789e233305f50c0f6f
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:225da166a3567479b467edbd66cc5540e5fb9e21ad5559249bc60343e8aa02cb
+oid sha256:78b522addaf0562d6804ca14f05b7612546f36db18c9447cb63a2360b49b82fb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6c398f06d76c43e8804ec85a57336d4caa4a253171be4f5a124c97886f31616
+oid sha256:06b9e247c644d88c6b75288b062ce133bd318a7b3c27e9c864410974153f4cd6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5424,
+  "epoch": 0.5472,
   "eval_steps": 500,
-  "global_step": 6780,
+  "global_step": 6840,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2380,6 +2380,27 @@
       "learning_rate": 2.3094745108254437e-05,
       "loss": 3.5111,
       "step": 6780
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 26.23602867126465,
+      "learning_rate": 2.305380260473476e-05,
+      "loss": 3.4637,
+      "step": 6800
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 32.71681213378906,
+      "learning_rate": 2.3012775620636747e-05,
+      "loss": 3.4752,
+      "step": 6820
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 55.637813568115234,
+      "learning_rate": 2.2971664586314055e-05,
+      "loss": 3.531,
+      "step": 6840
     }
   ],
   "logging_steps": 20,
@@ -2387,7 +2408,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 1.6009810231689216e+16,
+  "total_flos": 1.6145823545229312e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null