Training in progress, step 45, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:298516dbcdfb6f71f47cd7ef45620b1a7780cc860fe07420c135805c1714ff23
+oid sha256:e699f53036be930bd5a63812569f6cf296f07103e20241e7ef31901c03259100
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65418715ce8a6fdccb45c3ad7a5db6512f82c50e94390bd38ab1df68795dc803
+oid sha256:71b279796636ec685c3a045acd09ad93e4f043d93e66a782c426447171d83721
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:149ce6f9fed784895c9f3e27043159b254515601069bd04b971d74fdaafd4f26
+oid sha256:34899b4e0c2b02ca41e3b7d529ba4a9f07943c5a443b8133731540fec677b605
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc389ed2ec8a0148b9b29024154a8f2f11c6a7454ef1d0724563562d03a46e01
+oid sha256:9776c8df8be516beee92201f32f4a3f5d90539bf47f8ef27e1636cdc132a851e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01968019680196802,
+  "epoch": 0.024600246002460024,
   "eval_steps": 9,
-  "global_step": 36,
+  "global_step": 45,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -131,6 +131,35 @@
       "eval_samples_per_second": 7.221,
       "eval_steps_per_second": 0.905,
       "step": 36
+    },
+    {
+      "epoch": 0.02132021320213202,
+      "grad_norm": 0.19672754406929016,
+      "learning_rate": 3.824798160583012e-05,
+      "loss": 0.6362,
+      "step": 39
+    },
+    {
+      "epoch": 0.022960229602296024,
+      "grad_norm": 0.23685137927532196,
+      "learning_rate": 3.5959278669726935e-05,
+      "loss": 0.6394,
+      "step": 42
+    },
+    {
+      "epoch": 0.024600246002460024,
+      "grad_norm": 0.2077840119600296,
+      "learning_rate": 3.355050358314172e-05,
+      "loss": 0.6716,
+      "step": 45
+    },
+    {
+      "epoch": 0.024600246002460024,
+      "eval_loss": 0.640738308429718,
+      "eval_runtime": 426.7745,
+      "eval_samples_per_second": 7.219,
+      "eval_steps_per_second": 0.904,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -150,7 +179,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.453645871448064e+16,
+  "total_flos": 1.1833584692232192e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null