Training in progress, step 44, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea615d725d352c698298f1aafb52aa98c1a78228e503f077fb1850cd70175e4c
+oid sha256:76f91c6a2f061217f78f6a7609554ae95a6b657bf15b463033502ef72be15404
 size 200068512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:156dc99a94b1badd12ced5626ab6212100a80b454eb8dd97cf50e94195fdcc09
+oid sha256:92a92a305f9e0a704e8139eda03a762ad45b3e3b1e2c691be051989dd687ba82
 size 400361770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9716d25ba59b99bcb755bf9d1d3a4bbfaffe5d4cb0c0c8a773bcf7e9f59b7418
+oid sha256:76fa3c41cc968cfb5f9d5b60a53b0b1916c4810ccf20412b25d75e05e11a5190
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c792918044964431737f4cb39f3769dbfd230048b1125ac69a6439eb6c8534b
+oid sha256:7ed6431293c03d1e193e9501dc8ed4f4955bf079fba7f2c1c309a3efed166e50
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.010767884783632815,
+  "epoch": 0.011844673261996097,
   "eval_steps": 4,
-  "global_step": 40,
+  "global_step": 44,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -375,6 +375,42 @@
       "eval_samples_per_second": 8.289,
       "eval_steps_per_second": 4.147,
       "step": 40
+    },
+    {
+      "epoch": 0.011037081903223635,
+      "grad_norm": 2.763805389404297,
+      "learning_rate": 2.3959403439996907e-05,
+      "loss": 3.7855,
+      "step": 41
+    },
+    {
+      "epoch": 0.011306279022814456,
+      "grad_norm": 2.3128108978271484,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 3.494,
+      "step": 42
+    },
+    {
+      "epoch": 0.011575476142405276,
+      "grad_norm": 3.1583259105682373,
+      "learning_rate": 1.4735983564590783e-05,
+      "loss": 4.1824,
+      "step": 43
+    },
+    {
+      "epoch": 0.011844673261996097,
+      "grad_norm": 2.4732134342193604,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 3.8976,
+      "step": 44
+    },
+    {
+      "epoch": 0.011844673261996097,
+      "eval_loss": 3.8724188804626465,
+      "eval_runtime": 187.5642,
+      "eval_samples_per_second": 8.344,
+      "eval_steps_per_second": 4.175,
+      "step": 44
     }
   ],
   "logging_steps": 1,
@@ -394,7 +430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.067577446170624e+16,
+  "total_flos": 3.3743351907876864e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null