Training in progress, step 860, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:110e40ef4e3b35e43c4b8e29cc4d8dacba6d280f69bc8a29bf2ea57136d99510
+oid sha256:a7261173c6cc37f0af738ac4f62cf733cb9f189924cfe1daf21367523618d8ed
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f714a7f3ccb21a9df52dd325a7b732a1a6695dc5d620393c7f1ac8fb9f416e45
+oid sha256:cac75987c36eb3aed135202de0ad0e205dc153c722e06aec3f39d75285a9d2aa
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f65c5ab9da6e46829bd259bc0530be4e36f97ecb7b4f497275a1a99eb3a6c3bc
+oid sha256:9216bd0d63331af67d42e3e886e98fe378c7f9e63ccf40fc65dc43479bba4269
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8606193994762bc6fbc4224c0c881800eb5d3299a457924ce427b06d77b4771d
+oid sha256:edcbda48b98381d2804df29839fc6b7baea1aebc4a5832ba4c600db41135c488
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0672,
+  "epoch": 0.0688,
   "eval_steps": 500,
-  "global_step": 840,
+  "global_step": 860,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -301,6 +301,13 @@
       "learning_rate": 2.9988672727066197e-05,
       "loss": 3.7201,
       "step": 840
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 28.671123504638672,
+      "learning_rate": 2.9986706477143436e-05,
+      "loss": 3.6594,
+      "step": 860
     }
   ],
   "logging_steps": 20,
@@ -308,7 +315,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 1985676276400128.0,
+  "total_flos": 2034589892050944.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null