Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4dec8d0fa398d19284243db98da1895f9df8f774f6e783ddcbd8a30a39692a51
+oid sha256:80c10a1d0bc4a67741c0456f1c82fa3586dfc830e52f597fb154e48f5c129cce
 size 8137792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d50fd627c988db3d38fa12faab23c6257f1b228abd9bcd7a2dce297373c54d5
+oid sha256:572abda7230a4b1baad9d40d33fef79b7be071434dab3eb2c57f73a6cb179d26
 size 16386426

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87e68d4096ff4a2bcfeab02a4d13792c50d670e6a72d617f09279beb1398b03c
+oid sha256:08bcb3c55d75ccee08f69acbadd769dfd42aa5e730eb584778f328649f09efbd
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01975b1a1b88122c3881ce9e3f1ac623f0314fe73598789a1e034aed8c61c3c2
+oid sha256:2768ee351c2ec824b937dead00b6b93e0fdcbac2ed5ad3356408305263260d0f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.19996875488204968,
+  "epoch": 0.39993750976409936,
   "eval_steps": 500,
-  "global_step": 100,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -14,6 +14,13 @@
       "learning_rate": 9.933333333333334e-05,
       "loss": 1.66,
       "step": 100
+    },
+    {
+      "epoch": 0.39993750976409936,
+      "grad_norm": 0.07075967639684677,
+      "learning_rate": 9.866666666666668e-05,
+      "loss": 1.4581,
+      "step": 200
     }
   ],
   "logging_steps": 100,
@@ -33,7 +40,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.5607497118816666e+17,
+  "total_flos": 3.121499423763333e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null