Training in progress, step 580, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7af6ede55d0341241bc32219ef506f81ee7d0a6598b2c326b762b273b49ba7c
+oid sha256:423887fe77f4e0baaa663ac930e3bec81e8cf72266035e2f077c059a4f29b9aa
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d712e257f17863cb11322f71673372ff307ede78b55ed17a21b191a03b5a310
+oid sha256:2a3a9eef98c4e03dca15f1fb920809d2513c26c4e4d80ec79ee9def992aef167
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:813c071ac276f83e1b6d20b4afa7012ff50b1e905202a7b0d6045d0bc7d97762
+oid sha256:c628140ac361731721c9a78828173eec4d00472815f19e4c30739bcc5f9a3440
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fda21cee6c433e296b92e0e41eec8879af8f118fc5a2faf949201c0875cc586
+oid sha256:a82ddc2c8aea33997924d2c7f637842a8fb10ce7ce6b85d2cc712db7c0b67d47
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2003577817531306,
+  "epoch": 0.2075134168157424,
   "eval_steps": 500,
-  "global_step": 560,
+  "global_step": 580,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -455,14 +455,30 @@
       "loss": 0.4329,
       "num_input_tokens_seen": 373196,
       "step": 560
+    },
+    {
+      "epoch": 0.2039355992844365,
+      "grad_norm": 0.36333030462265015,
+      "learning_rate": 0.0001592128801431127,
+      "loss": 0.4482,
+      "num_input_tokens_seen": 380449,
+      "step": 570
+    },
+    {
+      "epoch": 0.2075134168157424,
+      "grad_norm": 0.2979726195335388,
+      "learning_rate": 0.00015849731663685151,
+      "loss": 0.4258,
+      "num_input_tokens_seen": 386577,
+      "step": 580
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 373196,
+  "num_input_tokens_seen": 386577,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 8391860138631168.0,
+  "total_flos": 8692751575074816.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null