Training in progress, step 40, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e6697448a47b73db7934d4c78af2c93ff8aed20e6e7547d19820928cfcfb717
+oid sha256:8b4091c38dfe36d1d998b9f8c228df7b1e9b7407d62438d52a58ddfce473fb8e
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb5eb51b4d96f09d2b7647c197cb2304b989f8ab6e905efd7b6ccdac2467d972
+oid sha256:0c73588560c8a69080f8336901f856b9982346011b066bf0ad41e2ce20951d95
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd9ce5f4ad85d6f975caf6b377b16ebf11a71e9e6883f50fa5c16baa4a8a21e4
+oid sha256:4c5a461af89936754c35931f95b98664491a8f9acb3a39a97a78b0e7b57c4c0e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab90a065c15d0d94012af603082a0a02f91866951ddb71c99f4bda63cd8ebbd2
+oid sha256:f69d738212e5843d2504ae60ce61d4198b9f8df55970cc251ec9a8253d284849
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.007155635062611807,
+  "epoch": 0.014311270125223614,
   "eval_steps": 500,
-  "global_step": 20,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -23,14 +23,30 @@
       "loss": 0.5478,
       "num_input_tokens_seen": 13063,
       "step": 20
+    },
+    {
+      "epoch": 0.01073345259391771,
+      "grad_norm": 0.3872911036014557,
+      "learning_rate": 0.00019785330948121648,
+      "loss": 0.5135,
+      "num_input_tokens_seen": 19512,
+      "step": 30
+    },
+    {
+      "epoch": 0.014311270125223614,
+      "grad_norm": 0.4991438686847687,
+      "learning_rate": 0.0001971377459749553,
+      "loss": 0.5092,
+      "num_input_tokens_seen": 26884,
+      "step": 40
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 13063,
+  "num_input_tokens_seen": 26884,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 293740739426304.0,
+  "total_flos": 604526222057472.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null