Training in progress, step 6780, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bb5fc18755b1bc902fa960b0f60645e025420e2f705caa8dd38fa32ba2a515f
+oid sha256:720b003068dffa8262fc19d67635315f97ac650b263fd177d92adc68b5e84fe8
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba29c27cd92ae55f3cbe6a02b6f053222af12f4509080505a7f771088cee1368
+oid sha256:370ab4cbab2424ee9196b0433c81cdf1630c4c010b17101af78d131d7e230efe
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efc7a7c74bad975dd9444229576dbd2c0f4d486da085dd3b0799e3c2cfd1606c
+oid sha256:225da166a3567479b467edbd66cc5540e5fb9e21ad5559249bc60343e8aa02cb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab72aa2c0b933f851e99251a29f0e0981ef1d4f3067a1de99a80ef1648d5af32
+oid sha256:e6c398f06d76c43e8804ec85a57336d4caa4a253171be4f5a124c97886f31616
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5392,
+  "epoch": 0.5424,
   "eval_steps": 500,
-  "global_step": 6740,
+  "global_step": 6780,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2366,6 +2366,20 @@
       "learning_rate": 2.3176374956579525e-05,
       "loss": 3.4748,
       "step": 6740
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 41.864219665527344,
+      "learning_rate": 2.3135602701728302e-05,
+      "loss": 3.4859,
+      "step": 6760
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 48.69860076904297,
+      "learning_rate": 2.3094745108254437e-05,
+      "loss": 3.5111,
+      "step": 6780
     }
   ],
   "logging_steps": 20,
@@ -2373,7 +2387,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 1.5917855258738688e+16,
+  "total_flos": 1.6009810231689216e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null