Training in progress, step 2740, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2311db336a74d6027b311eaa653056cb4acaddc6053a9bcfcf31ef286760d5ed
+oid sha256:8dac76252f1ea6c454a23d0bbec6eeaeb8d90dfaad35efd9ad30249ccf2119c5
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ccc45fddbbe9d221c9887609118bdcd89634d9fbc115859deaaa180775d1c41
+oid sha256:729d204eef78583ce2389cfa7dc8cda2ae4e1adb786f8db9dc5f44cb7ecb07b8
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f3423ef0180b7cc49d51ed48a15845d80402981893f5feeedb16a233a66fd87
+oid sha256:a5dcb69f4ac177e15c15ecfe217e43f79f5c314ca2c667a27bad7ba64f808dd4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3791c6b28f2569893f2f7130add08063530eee9e29c0d2d9ebca8117edde234
+oid sha256:9f9ea2eb042c7e9028c8b0fad7dc94246e12807e86516795fbebc04c9df82814
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9731663685152058,
+  "epoch": 0.9803220035778175,
   "eval_steps": 500,
-  "global_step": 2720,
+  "global_step": 2740,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2183,14 +2183,30 @@
       "loss": 0.3393,
       "num_input_tokens_seen": 1844328,
       "step": 2720
+    },
+    {
+      "epoch": 0.9767441860465116,
+      "grad_norm": 0.3002487123012543,
+      "learning_rate": 4.651162790697674e-06,
+      "loss": 0.358,
+      "num_input_tokens_seen": 1850313,
+      "step": 2730
+    },
+    {
+      "epoch": 0.9803220035778175,
+      "grad_norm": 0.29295697808265686,
+      "learning_rate": 3.935599284436494e-06,
+      "loss": 0.3986,
+      "num_input_tokens_seen": 1857019,
+      "step": 2740
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 1844328,
+  "num_input_tokens_seen": 1857019,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 4.147242367485542e+16,
+  "total_flos": 4.175779944795955e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null