Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c99a17e61167bdd22027d5e74d6950bc7fccc49a5763828724aea074a8d7b1d
+oid sha256:188eeb86ef22fe0a859a7a70627a7f2148904fbb59b0e35a1ecb549e6efe65ee
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:235d71225018e2bbba6d0edf1a30d2d5fbbf49bed103f705d28c8cf7fc0e6120
+oid sha256:c980c4ec7c96f1817eb0e5876cdb98423414ae5a1f74709f44120e3ff20823fb
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c143614aa475513a4db1c2c5778c359a2fbe173dda8313ed145dc946741a2fbe
+oid sha256:6782a17cd94b88584cdd39e48a03aa9ee53aa99ebb01a7ca50bd04caffebba8e
 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": 0.00046687629412272777,
+  "epoch": 0.0009337525882454555,
   "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": 32.104,
       "eval_steps_per_second": 16.052,
       "step": 50
+    },
+    {
+      "epoch": 0.0005602515529472734,
+      "grad_norm": 6.204837799072266,
+      "learning_rate": 0.00016324453755953773,
+      "loss": 0.8176,
+      "step": 60
+    },
+    {
+      "epoch": 0.0006536268117718189,
+      "grad_norm": 4.421334743499756,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.6348,
+      "step": 70
+    },
+    {
+      "epoch": 0.0007470020705963644,
+      "grad_norm": 5.26912260055542,
+      "learning_rate": 0.00013546048870425356,
+      "loss": 0.5701,
+      "step": 80
+    },
+    {
+      "epoch": 0.0008403773294209099,
+      "grad_norm": 12.316139221191406,
+      "learning_rate": 0.00012000256937760445,
+      "loss": 0.4992,
+      "step": 90
+    },
+    {
+      "epoch": 0.0009337525882454555,
+      "grad_norm": 7.5016350746154785,
+      "learning_rate": 0.00010402659401094152,
+      "loss": 0.4787,
+      "step": 100
+    },
+    {
+      "epoch": 0.0009337525882454555,
+      "eval_loss": 0.13443197309970856,
+      "eval_runtime": 1402.4134,
+      "eval_samples_per_second": 32.154,
+      "eval_steps_per_second": 16.077,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -77,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8763353962905600.0,
+  "total_flos": 1.75267079258112e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null