Training in progress, step 1360, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a6ef45bd2c6657e274eedc49f26c23b179266791961c2a152bdc744f41db6d9
+oid sha256:b4c36ddd34e5f64d6b8d72f7535780e3421a848c056451338ad60b3bc23355ca
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef263273d0bcb84c538ed1445bbe5e4a6295597c291e697247084cb716e21d2b
+oid sha256:d8441702a5d48998055bebf8bf17f52c9868b1176bcfd106766c5daef35e2005
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:374445db7d4c85dfe9a467237f38a6547820c3f8438ea4ab81171e3d5f8f6ee3
+oid sha256:a125d9b0ccf3b1e15af9c78c7573f334a287768d58700d4bae393ced8e6486ba
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec78e29e996a7a82367bd352bbf299a68c1222533fc8b32296b57f73e7e1b03b
+oid sha256:9822ffd7b1cdab49a87c2ee8fe2f970274c45f8492d363a6e7b14647c57922bd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.47942754919499103,
+  "epoch": 0.4865831842576029,
   "eval_steps": 500,
-  "global_step": 1340,
+  "global_step": 1360,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1079,14 +1079,30 @@
       "loss": 0.4353,
       "num_input_tokens_seen": 902631,
       "step": 1340
+    },
+    {
+      "epoch": 0.48300536672629696,
+      "grad_norm": 0.2746681571006775,
+      "learning_rate": 0.0001033989266547406,
+      "loss": 0.3863,
+      "num_input_tokens_seen": 908599,
+      "step": 1350
+    },
+    {
+      "epoch": 0.4865831842576029,
+      "grad_norm": 0.3950134813785553,
+      "learning_rate": 0.00010268336314847943,
+      "loss": 0.4049,
+      "num_input_tokens_seen": 915272,
+      "step": 1360
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 902631,
+  "num_input_tokens_seen": 915272,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 2.029698364610765e+16,
+  "total_flos": 2.0581235095781376e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null