Training in progress, step 2060, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e47362b6d0eac1f82180e6b29ee3f7c2d915006bc065406131a0fd35b2efbbc1
+oid sha256:aacd2486ad0dffb879950bbd0e228566072cada12669efb472827ad02827bee1
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd11da65ffb0d4570e59961b0c132d6bd8b1f1fdc0c2f1a395db947863533b9d
+oid sha256:c5211b09fe504a464e43c55dfc38d2344163312b5195fd5daf7f89e63f7ced18
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68d8d961de9fa331face7d8cad742caf1cb05dec24ac6128db0c9c0b06d4b11b
+oid sha256:134cb87f21fc79818d41b8f638e21e286fa4116529d636e02de189068c5b06fb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1f92df614fc27cf99bd5eb65435800e9a0c33f53a2b39dfcb3917ef6db37df5
+oid sha256:b5b38b213077a686f76d4c3ad3d757ef1baf287b742f46835bdf0d82ea6cc979
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7298747763864043,
+  "epoch": 0.7370304114490162,
   "eval_steps": 500,
-  "global_step": 2040,
+  "global_step": 2060,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1639,14 +1639,30 @@
       "loss": 0.3981,
       "num_input_tokens_seen": 1382038,
       "step": 2040
+    },
+    {
+      "epoch": 0.7334525939177102,
+      "grad_norm": 0.37042665481567383,
+      "learning_rate": 5.3309481216457965e-05,
+      "loss": 0.3949,
+      "num_input_tokens_seen": 1388519,
+      "step": 2050
+    },
+    {
+      "epoch": 0.7370304114490162,
+      "grad_norm": 0.3565654754638672,
+      "learning_rate": 5.2593917710196785e-05,
+      "loss": 0.3869,
+      "num_input_tokens_seen": 1395702,
+      "step": 2060
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 1382038,
+  "num_input_tokens_seen": 1395702,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 3.1077154102063104e+16,
+  "total_flos": 3.1384409209122816e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null