Training in progress, step 600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:423887fe77f4e0baaa663ac930e3bec81e8cf72266035e2f077c059a4f29b9aa
+oid sha256:7e4aa0619718301c4cee6a46cec390e99f468dbc3294652a09dad80c2c1c52ac
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a3a9eef98c4e03dca15f1fb920809d2513c26c4e4d80ec79ee9def992aef167
+oid sha256:2f3f0d6d31265332cf0153ce373f616a507a1b2bdb68c61151d6f231efb64720
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c628140ac361731721c9a78828173eec4d00472815f19e4c30739bcc5f9a3440
+oid sha256:5a3896f4879562a69571237c21fd91dc0cba3215ed23fb9ae7f0374432fee52f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a82ddc2c8aea33997924d2c7f637842a8fb10ce7ce6b85d2cc712db7c0b67d47
+oid sha256:a18b7d573288acd75186bfa1799a658370b6b400daf569612aa7a4ba8b0298a1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2075134168157424,
+  "epoch": 0.2146690518783542,
   "eval_steps": 500,
-  "global_step": 580,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -471,14 +471,30 @@
       "loss": 0.4258,
       "num_input_tokens_seen": 386577,
       "step": 580
+    },
+    {
+      "epoch": 0.2110912343470483,
+      "grad_norm": 0.2969113886356354,
+      "learning_rate": 0.00015778175313059035,
+      "loss": 0.433,
+      "num_input_tokens_seen": 392953,
+      "step": 590
+    },
+    {
+      "epoch": 0.2146690518783542,
+      "grad_norm": 0.4132014811038971,
+      "learning_rate": 0.00015706618962432918,
+      "loss": 0.4148,
+      "num_input_tokens_seen": 399368,
+      "step": 600
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 386577,
+  "num_input_tokens_seen": 399368,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 8692751575074816.0,
+  "total_flos": 8980375995039744.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null