Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02d09f7e86d3d96aea548d4c29d905e7fb7ec7feb0edb7c99fe23bb63fdaf77a
+oid sha256:f2aa39907dc5ef3b94d502a5b8fd7e2741bc930c5b38483d70042aba0e7a8576
 size 125040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:268617e542391debaa2778c3f8688202c00300fef3f9a8e448a59680e416fa42
+oid sha256:3d6a862bbbd5abb505758d4ad7e6770678d34ccefa06b7a1a6932483ba5dde72
 size 162868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5436a3bbf37287d16586b122bf08a6503be8f105d9eb90735d86c731387351db
+oid sha256:c3b91b616bd452b894e1aea50022754f9be4afc2c867b79623be361a63b980b2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8148b27980adb9b0bdd5c04049e531bfefcc05c06612ee72169cfb9b9fd7ee7
+oid sha256:0fd8212ec5ec3406d74a7f927b717dd30ea8a06115ee6582e14976f7b84b4b58
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.012444001991040319,
+  "epoch": 0.024888003982080638,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 410.079,
       "eval_steps_per_second": 205.039,
       "step": 50
+    },
+    {
+      "epoch": 0.014932802389248382,
+      "grad_norm": 2.52058482170105,
+      "learning_rate": 0.00016324453755953773,
+      "loss": 43.87,
+      "step": 60
+    },
+    {
+      "epoch": 0.017421602787456445,
+      "grad_norm": 2.31777286529541,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 43.7613,
+      "step": 70
+    },
+    {
+      "epoch": 0.019910403185664508,
+      "grad_norm": 2.353991746902466,
+      "learning_rate": 0.00013546048870425356,
+      "loss": 43.646,
+      "step": 80
+    },
+    {
+      "epoch": 0.022399203583872575,
+      "grad_norm": 2.1439247131347656,
+      "learning_rate": 0.00012000256937760445,
+      "loss": 43.5494,
+      "step": 90
+    },
+    {
+      "epoch": 0.024888003982080638,
+      "grad_norm": 2.1935505867004395,
+      "learning_rate": 0.00010402659401094152,
+      "loss": 43.4825,
+      "step": 100
+    },
+    {
+      "epoch": 0.024888003982080638,
+      "eval_loss": 10.841394424438477,
+      "eval_runtime": 4.1228,
+      "eval_samples_per_second": 410.396,
+      "eval_steps_per_second": 205.198,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -77,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 482240102400.0,
+  "total_flos": 964480204800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null