Training in progress, step 1080, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83db771df950e62ad2023cec1215f51219493e18859b93162135ea811647b4ee
+oid sha256:6bad098bfc3580a7ad640c4130e7a07c7506695bf24af2b17c66a370a46a96ea
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6b7dbda1b23eed1009be33bc92a27f23738750bb760895a3877eb8413e63752
+oid sha256:a1678b1a77440b4735ea8dca5d633374798805380e60f92032e0e8dfb0faedde
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7097ad8e44eb73dccc917ee5a890bd970cf5e65b02ff96ff5daa468616d769c6
+oid sha256:2f5f93394ec4ac2c9202e96d8f2c28e904b14601df40e2aa991afd31d35337d4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2ed300d9a9b5101b0a51972c41bba244062680bd71a8f222001fe6d7c1bf120
+oid sha256:dee088d40e7a433523254925268530a7e4fe462e4869c9eeb52cf75236d3eadf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.37924865831842575,
+  "epoch": 0.38640429338103754,
   "eval_steps": 500,
-  "global_step": 1060,
+  "global_step": 1080,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -855,14 +855,30 @@
       "loss": 0.4317,
       "num_input_tokens_seen": 710659,
       "step": 1060
+    },
+    {
+      "epoch": 0.3828264758497317,
+      "grad_norm": 0.31499966979026794,
+      "learning_rate": 0.00012343470483005368,
+      "loss": 0.4357,
+      "num_input_tokens_seen": 717932,
+      "step": 1070
+    },
+    {
+      "epoch": 0.38640429338103754,
+      "grad_norm": 0.4409402012825012,
+      "learning_rate": 0.0001227191413237925,
+      "loss": 0.408,
+      "num_input_tokens_seen": 724716,
+      "step": 1080
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 710659,
+  "num_input_tokens_seen": 724716,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 1.5980211294492672e+16,
+  "total_flos": 1.6296303583715328e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null