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:fae818c11675d199a9c7ca2c355b4caed3ad33e14ad2f4a9db0ed15ac1186f9f
+oid sha256:ca2ef0261b9297e57eb0e6889cbd70bd9fc32b7ddb742c7a9bd122e427882cb1
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc1f76dd5ab649ca72bfe988e5db26e67c4889add94764ff40842ba584301846
+oid sha256:623c8669599ab8606c91a89f68efd3817190db7cebdd8f7009d841dfbc06cf13
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1d6e1fa09234a6b9aeabf5e7a61d21b1152d5256cf463aede866e5f4c72a842
+oid sha256:c512fb5e6f5d109f5378fc46a214147599d5eb7b9ff95241caad816b4b88a833
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b80fcc7599efca0c6313d990c467c2eb3001742b23ddaadc22e3499c12cea79
+oid sha256:81007ec48272bbdc4f9622c046f9c026bf8120ed11d1398fd97bb5168a6f3dda
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.02304147465437788,
+  "epoch": 0.04608294930875576,
   "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": 27.76,
       "eval_steps_per_second": 13.88,
       "step": 50
+    },
+    {
+      "epoch": 0.027649769585253458,
+      "grad_norm": 0.9648954272270203,
+      "learning_rate": 0.0002,
+      "loss": 1.2425,
+      "step": 60
+    },
+    {
+      "epoch": 0.03225806451612903,
+      "grad_norm": 1.180851697921753,
+      "learning_rate": 0.0002,
+      "loss": 1.1576,
+      "step": 70
+    },
+    {
+      "epoch": 0.03686635944700461,
+      "grad_norm": 0.9131804704666138,
+      "learning_rate": 0.0002,
+      "loss": 1.1993,
+      "step": 80
+    },
+    {
+      "epoch": 0.041474654377880185,
+      "grad_norm": 0.9733966588973999,
+      "learning_rate": 0.0002,
+      "loss": 1.2544,
+      "step": 90
+    },
+    {
+      "epoch": 0.04608294930875576,
+      "grad_norm": 1.0335547924041748,
+      "learning_rate": 0.0002,
+      "loss": 1.223,
+      "step": 100
+    },
+    {
+      "epoch": 0.04608294930875576,
+      "eval_loss": 1.1788889169692993,
+      "eval_runtime": 32.9063,
+      "eval_samples_per_second": 27.776,
+      "eval_steps_per_second": 13.888,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -77,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1370700200738816e+16,
+  "total_flos": 2.2828532203782144e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null