Training in progress, step 2380, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd0aba29ef3bfaae1191218954a63d90da222aed22aa2200b611cf74f049d222
+oid sha256:3595b12f86459195f8d09179d7c0dbf8792ab5da530439f3a09a0bba7f7a42a1
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d8cd6e4f50429cda27a28378dce5408f87f0a91096366b51efe3dd54bb9f0e0
+oid sha256:58fbfe5c5eaca18bcc1c80efd605fd210e276ac78ec3e25b0dac1bfe7a2ee3d1
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3eea0d25f64360cae73a775ba2c6c88f883be49aa9244b8f3d005a3b98fa5466
+oid sha256:c99e1271397b81fc889fdb77bb7999277542aa1b382e9e22a5a0bd0cd0a478e3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:328a8cc6caa8e9e02ff012a126152b40a2427772a86d6a8867f005290455d35c
+oid sha256:5d5e00b537e62e61b7fa13230cc02b759e6748bf2bcdb20f27dd8576bd1d7344
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8443649373881932,
+  "epoch": 0.851520572450805,
   "eval_steps": 500,
-  "global_step": 2360,
+  "global_step": 2380,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1895,14 +1895,30 @@
       "loss": 0.3722,
       "num_input_tokens_seen": 1601444,
       "step": 2360
+    },
+    {
+      "epoch": 0.8479427549194991,
+      "grad_norm": 0.44683215022087097,
+      "learning_rate": 3.041144901610018e-05,
+      "loss": 0.4009,
+      "num_input_tokens_seen": 1607535,
+      "step": 2370
+    },
+    {
+      "epoch": 0.851520572450805,
+      "grad_norm": 0.3482876121997833,
+      "learning_rate": 2.9695885509839e-05,
+      "loss": 0.3792,
+      "num_input_tokens_seen": 1615204,
+      "step": 2380
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 1601444,
+  "num_input_tokens_seen": 1615204,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 3.601082023346995e+16,
+  "total_flos": 3.632023404151603e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null