Training in progress, step 1340, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f11665d8738bbd240d3d64a2d0c1f1d475eca89083c256901ae805bbe967af82
+oid sha256:5a6ef45bd2c6657e274eedc49f26c23b179266791961c2a152bdc744f41db6d9
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbc2f3fdb0d50fd60d43dd5cec54d8b57e44e12546132c2401b5262cbdbd22a8
+oid sha256:ef263273d0bcb84c538ed1445bbe5e4a6295597c291e697247084cb716e21d2b
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae7829701acac442ef32175bc209c900d8742812b8a1a981592f253b573d17b2
+oid sha256:374445db7d4c85dfe9a467237f38a6547820c3f8438ea4ab81171e3d5f8f6ee3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a38e6a44e6657eed373e3587573685b30a045b1ada672c0864a1f76b235fdfd
+oid sha256:ec78e29e996a7a82367bd352bbf299a68c1222533fc8b32296b57f73e7e1b03b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.47227191413237923,
+  "epoch": 0.47942754919499103,
   "eval_steps": 500,
-  "global_step": 1320,
+  "global_step": 1340,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1063,14 +1063,30 @@
       "loss": 0.4092,
       "num_input_tokens_seen": 888281,
       "step": 1320
+    },
+    {
+      "epoch": 0.47584973166368516,
+      "grad_norm": 0.31455397605895996,
+      "learning_rate": 0.00010483005366726297,
+      "loss": 0.3943,
+      "num_input_tokens_seen": 895446,
+      "step": 1330
+    },
+    {
+      "epoch": 0.47942754919499103,
+      "grad_norm": 0.25797346234321594,
+      "learning_rate": 0.0001041144901610018,
+      "loss": 0.4353,
+      "num_input_tokens_seen": 902631,
+      "step": 1340
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 888281,
+  "num_input_tokens_seen": 902631,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 1.997430282158285e+16,
+  "total_flos": 2.029698364610765e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null