Training in progress, step 1000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a38c93e994650fe4c83da9cfce04fe1541ec31a2ec6907ff09b91f14be34ad4d
+oid sha256:cfd440a6a9224314ef21aafd465b94d6530d5c01c5a6d9a47f538f4bbec5a7f7
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46cbd28b8ea82d833a6eeaf797d7e79113fcfd64f188a19553eb3bcd4a1e3573
+oid sha256:a58ecbba4795d91002286a176932989cf3c4702e47563235dfca4a3d9993ec27
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c5410d295859629eb5c5221ec007a76d5ecce5c325cbaeb984aecc19e1cfef7
+oid sha256:e50cdb03a68599393cddfdbebcebb37585c7ac7298ee17a142301421a973eb67
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1deaeac856492d3d5086d74c9dfcab210016322b2b2c1701903eaa6e0b81545c
+oid sha256:97a179414ff6ad0a212e3db071454cbcaf0d4c464019d7d52756a35e2df240c7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0784,
+  "epoch": 0.08,
   "eval_steps": 500,
-  "global_step": 980,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -350,6 +350,13 @@
       "learning_rate": 2.9971608542252175e-05,
       "loss": 3.7077,
       "step": 980
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 25.48147201538086,
+      "learning_rate": 2.9968542393565674e-05,
+      "loss": 3.6721,
+      "step": 1000
     }
   ],
   "logging_steps": 20,
@@ -357,7 +364,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 2331220953563136.0,
+  "total_flos": 2376099441967104.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null