Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f5affae5bd9b31a10efaae0e759147a9f84f4cb46a6944bc87c10754a50d842
+oid sha256:32572b5a6c06368970b49abb13ed7be8c1738fb1bab0e84c899b421beda46f8b
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd4cc65ffa30e6284397ad0b1b17d5d34c50e675b63c391b3197ef096524c790
+oid sha256:15b0f60be9a6e6fa935484f4ba43ed8ef0f82ce28417e3525e24e9ae75110d2c
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fac8dc3559aa6a81370bb141163d5dc06aeeb8795a754c1c7ff70e9049a5afd
+oid sha256:07d77b60a4a6ac9b1290011cfbb000725f2f3c555f2baada62884afb493a185f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.011483253588516746,
+  "epoch": 0.022966507177033493,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 10.612,
       "eval_steps_per_second": 5.306,
       "step": 3
+    },
+    {
+      "epoch": 0.015311004784688996,
+      "grad_norm": 0.3879363536834717,
+      "learning_rate": 8e-05,
+      "loss": 1.7923,
+      "step": 4
+    },
+    {
+      "epoch": 0.019138755980861243,
+      "grad_norm": 0.36468327045440674,
+      "learning_rate": 0.0001,
+      "loss": 1.4935,
+      "step": 5
+    },
+    {
+      "epoch": 0.022966507177033493,
+      "grad_norm": 0.39484620094299316,
+      "learning_rate": 0.00012,
+      "loss": 1.5391,
+      "step": 6
+    },
+    {
+      "epoch": 0.022966507177033493,
+      "eval_loss": 1.7211520671844482,
+      "eval_runtime": 10.3763,
+      "eval_samples_per_second": 10.601,
+      "eval_steps_per_second": 5.301,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1899723258593280.0,
+  "total_flos": 3799446517186560.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null