Training in progress, step 1940, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b870a0e7956f1262db1a4c5aef5432c3ec742c8fde13bcd6f2e3c396586cb77
+oid sha256:6e4888f9f08518c6d58c830b271bb36cd465eedb56a20771aba351e68172f6cc
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51da4492196b6a9086d0a146412eb40e5ce7a1343c46940127cbd0a9a0bbdcb4
+oid sha256:6f5fea76bac96f4fa5b326844005d6d3b5178ec7b954adc7a2817b3325dbd873
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:664d1554b6d667624b0962efadcbe8a7a07a7fdf1f68db1a18116bf98d13cfb2
+oid sha256:6675257a869fc0efa3dc4f0df7900ffd4f952e0843913706c20ca08cfdb2c54f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a803c8c681e722b33ed0b628f93a55855af2e03fe7687b8b6a531e8a84502442
+oid sha256:f77432e61737c0e6ca92ad6d407da985441feb6cfec781ba12cb31c4ebbe3608
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6869409660107334,
+  "epoch": 0.6940966010733453,
   "eval_steps": 500,
-  "global_step": 1920,
+  "global_step": 1940,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1543,14 +1543,30 @@
       "loss": 0.374,
       "num_input_tokens_seen": 1299015,
       "step": 1920
+    },
+    {
+      "epoch": 0.6905187835420393,
+      "grad_norm": 0.3136894404888153,
+      "learning_rate": 6.189624329159213e-05,
+      "loss": 0.3952,
+      "num_input_tokens_seen": 1305291,
+      "step": 1930
+    },
+    {
+      "epoch": 0.6940966010733453,
+      "grad_norm": 0.3310141861438751,
+      "learning_rate": 6.118067978533095e-05,
+      "loss": 0.3968,
+      "num_input_tokens_seen": 1312434,
+      "step": 1940
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 1299015,
+  "num_input_tokens_seen": 1312434,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 2.921026001882112e+16,
+  "total_flos": 2.951200594107187e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null