Training in progress, step 6200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df13651e277a0c57568ab8ad1700485f28f93fce313b51d305bf49236a22d848
+oid sha256:814f9725a2fe2017d81c7865800e3fc5aaa4d89e46fab595b01bbf4f7f20db30
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f6d8560b09a8acbd520a643f2c903a1b4abe534eed07f393b76e7e3b4383130
+oid sha256:bfd0fc04c6dd797da3f4131745048e2e54e143452e73d060a7d4b95cdcc46ab1
 size 84581014

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:387d439f709c593f39d19f3e24beeef5450e32e99e883dfbed8c69aedc09f310
+oid sha256:d6abe2d849c4fd1f2d539f784dcb3eeec5c7c22dff6a560aa1f6ccd308e25b9e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db17511cf40c553b235e796d2decd760897da6988ddf690cb68bdac8e17c1364
+oid sha256:76d8049c15ee2a00e055cffd8620c280fe7aa42e36ed292a62ff445777eff25a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.004461978366841551,
+  "epoch": 0.004610710979069603,
   "eval_steps": 2000,
-  "global_step": 6000,
+  "global_step": 6200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -217,6 +217,13 @@
       "learning_rate": 1.999996084464646e-05,
       "loss": 1.6252,
       "step": 6000
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 1.8496161699295044,
+      "learning_rate": 1.9999958185831053e-05,
+      "loss": 1.5803,
+      "step": 6200
     }
   ],
   "logging_steps": 200,
@@ -224,7 +231,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 200,
-  "total_flos": 7.88654619022295e+16,
+  "total_flos": 8.142964605100032e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null