Training in progress, step 620, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e4aa0619718301c4cee6a46cec390e99f468dbc3294652a09dad80c2c1c52ac
+oid sha256:c42e3144125416adcb9a1ec0d9b0eb55619b6a3619ed6542a06de661bbf161b2
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f3f0d6d31265332cf0153ce373f616a507a1b2bdb68c61151d6f231efb64720
+oid sha256:9177ecdd03afda4d13d5d2eb2a0c1d5fbe522c00f0127e7917ebf328b282a0c8
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a3896f4879562a69571237c21fd91dc0cba3215ed23fb9ae7f0374432fee52f
+oid sha256:57a916e4fd36223dffeadbeb32e21c87fb935df188a4e2e19aafc7b1c3d84241
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a18b7d573288acd75186bfa1799a658370b6b400daf569612aa7a4ba8b0298a1
+oid sha256:398bdc23ac4d9e39643bb660fbaeca4b591289face79e5178809ed45f99c413b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2146690518783542,
+  "epoch": 0.22182468694096602,
   "eval_steps": 500,
-  "global_step": 600,
+  "global_step": 620,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -487,14 +487,30 @@
       "loss": 0.4148,
       "num_input_tokens_seen": 399368,
       "step": 600
+    },
+    {
+      "epoch": 0.2182468694096601,
+      "grad_norm": 0.35863760113716125,
+      "learning_rate": 0.000156350626118068,
+      "loss": 0.4105,
+      "num_input_tokens_seen": 407343,
+      "step": 610
+    },
+    {
+      "epoch": 0.22182468694096602,
+      "grad_norm": 0.287056028842926,
+      "learning_rate": 0.0001556350626118068,
+      "loss": 0.4495,
+      "num_input_tokens_seen": 413867,
+      "step": 620
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 399368,
+  "num_input_tokens_seen": 413867,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 8980375995039744.0,
+  "total_flos": 9306407303387136.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null