Training in progress, step 160, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e8d2c2b3997221c66bf79a833df524f3f6e85fb0677b22a3644d176660c25e3
+oid sha256:76c23eabae30233c18cd401c62f8e0fdf9b506e792f29593f372879ab9889061
 size 114106856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:973a7191ac7853359c6164a93246b598ef5b6481e5e3dbe6155eaa5f1e71fa76
+oid sha256:eba8d33d3d6dbe57b8d1cebb61ba0de9bad827bc491a92cb4a3b78ba6e7e530e
 size 58562260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb351b3a751c0869f15060cfb0448736e81516a42990e16dddc847a1f0524437
+oid sha256:08f9bcba87d2e0945a0f9440cfbe7c554cdfed46214f532e0f85019dae832107
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:080e787c96fa8b09f9b8bcf88f51a3766bad6b6691637c9fc0b084cb355db333
+oid sha256:500b1c78c9d3af1c55fbf9cc6e380394ac567579f265e54ad9607c3dc9f74108
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2728435412817962,
+  "epoch": 0.3637913883757283,
   "eval_steps": 40,
-  "global_step": 120,
+  "global_step": 160,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -60,6 +60,21 @@
       "eval_samples_per_second": 5.352,
       "eval_steps_per_second": 2.68,
       "step": 120
+    },
+    {
+      "epoch": 0.3637913883757283,
+      "grad_norm": 9.453910827636719,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 22.3112,
+      "step": 160
+    },
+    {
+      "epoch": 0.3637913883757283,
+      "eval_loss": 1.3575067520141602,
+      "eval_runtime": 138.7048,
+      "eval_samples_per_second": 5.342,
+      "eval_steps_per_second": 2.675,
+      "step": 160
     }
   ],
   "logging_steps": 40,
@@ -79,7 +94,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.5358528472481792e+17,
+  "total_flos": 2.0513689143607296e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null