Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b69e1ece531ae04226ab8e666c97b14f0d7a11afc5625e4c77a464e4ce29496
+oid sha256:29dd7ebae639bd2d9820d94f55a7d57ed7d7e651db6caee9214dbc394d6d8a52
 size 4725640

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbd9ad863a348d05efe28bd6743c02865fa3ef1f49db9e787ff7a2fb7012c27d
+oid sha256:69d66ca304d85c0c98fb0bf09060960ca796eb9eb4224559d90c4ff9e6ce0ba7
 size 2423802

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b08248ed26b28c1a0bd4b42e309ef4427a1e5fb6da926b6c61e6c6e7cc3b09fb
+oid sha256:23cf2bfaf6a90fad15e6cbfeee3986b0a34e7580afbe7ec2acc0dc8448accfb4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c08479d3d6dabb601d418ce802b775aad13d7bf7b26fde0b24c32b2a8f36ef6e
+oid sha256:bac6da347960aa710f0cf30015122a382ce8a8ef99042818f6297fe7974a65f2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00021791070330679492,
+  "epoch": 0.00023347575354299455,
   "eval_steps": 500,
-  "global_step": 280,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -105,6 +105,13 @@
       "learning_rate": 4.6500000000000005e-05,
       "loss": 2.6839,
       "step": 280
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 8.951983451843262,
+      "learning_rate": 4.9833333333333336e-05,
+      "loss": 2.7932,
+      "step": 300
     }
   ],
   "logging_steps": 20,
@@ -112,7 +119,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 1322195234439168.0,
+  "total_flos": 1405893996822528.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null