Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ce94eff600ba026131a58bb7c058f63a4eebaba5261d3d068b8d2d7209097e2
+oid sha256:dbc45dc11051d1f4864888a0e570e581995add708c6aacff93e5da70cc6ce514
 size 891333320

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d43b6381409c7630d2357322fdec9ec6b207ef8f033a699cb6cac51277a80b3d
+oid sha256:853389a394718aac5e4d7c0fbd9a79f4c580d0d231f97f88edfb3f59bdf314e0
 size 452984596

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18fb39841ebac4c6a16efba31e758b647140c6422f4a554fff4de99f10427bca
+oid sha256:25db4dbb2ba94e91727cce799620437c78e78810f53ff0628d41702c044b6ba4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d63217b923cb177f669d6bc2174b89abdc6a56d968d279b505491b37976d9bb
+oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0005534493732185849,
+  "epoch": 0.0011068987464371697,
   "eval_steps": 5,
-  "global_step": 5,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -30,6 +30,28 @@
       "eval_samples_per_second": 6.651,
       "eval_steps_per_second": 0.831,
       "step": 5
+    },
+    {
+      "epoch": 0.0006641392478623018,
+      "grad_norm": 38.565956115722656,
+      "learning_rate": 6e-05,
+      "loss": 58.5863,
+      "step": 6
+    },
+    {
+      "epoch": 0.0009962088717934527,
+      "grad_norm": 52.073787689208984,
+      "learning_rate": 9e-05,
+      "loss": 40.3884,
+      "step": 9
+    },
+    {
+      "epoch": 0.0011068987464371697,
+      "eval_loss": 3.4627695083618164,
+      "eval_runtime": 2290.4417,
+      "eval_samples_per_second": 6.643,
+      "eval_steps_per_second": 0.83,
+      "step": 10
     }
   ],
   "logging_steps": 3,
@@ -49,7 +71,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3781132378112e+16,
+  "total_flos": 2.7562264756224e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null