Training in progress, step 2340, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fca914b2057aa482eb7a6841c80c2efe9c097a9f40f833d983af4537dc40f6bb
+oid sha256:d8d9bb442ae601cf106b3006a0b171f810e2b1e6f85cad6fe3662e4f7d6b8c2b
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0648084ec0eae35cf7dd3a294bee444ad33f083ffa2a37e0110a6f2612622237
+oid sha256:fbbbb71c873d74aca94c35ba877c8558929a0c5a34e6a9bb657a8086f1f364b5
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5db6383b70031a203d8f79911eab63df2eb868f69d22da66a6d7b3fea0a2b6f6
+oid sha256:635cb17a2c9fedd045625390ceabdbcf7a1ac3172f61dcbc182e74aaba6c8f68
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4fa7f675de7d8161961ca1ab082c7d8425357c049f1a3dc57c1e35db98971b1
+oid sha256:4b2ca6293707bf7061331d560bd97d2236fd7b5ba46591c5449e07ebfb92b17b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1856,
+  "epoch": 0.1872,
   "eval_steps": 500,
-  "global_step": 2320,
+  "global_step": 2340,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -819,6 +819,13 @@
       "learning_rate": 2.9421897444138902e-05,
       "loss": 3.5913,
       "step": 2320
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 35.22037124633789,
+      "learning_rate": 2.9408464612887484e-05,
+      "loss": 3.5959,
+      "step": 2340
     }
   ],
   "logging_steps": 20,
@@ -826,7 +833,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 5493973373190144.0,
+  "total_flos": 5545413044109312.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null