Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53e100046bad02aa8795bb6d5922495b27c88ed4948d14bbd2da713babe5699f
+oid sha256:1826199ce99703a7d2d59648b49ee661301c1ea410965f9387eb99140722aea4
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c261a4d2f0733eaa1f3af190df879fff54eedd114cfa803ade74c2c83d00ea45
+oid sha256:21072423999cc222ac587607d166171f947ed78c90ac333ffbd138f589bf8a35
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0104c2c25b80b05f4aa46359191df58367bf4b542ff4aabbd3f340ab0f62cf58
+oid sha256:f7b286d49b95ae88580bf2c664acf642fad5bbdb5e1fe3eacfc43452c8836952
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4f8e4820960fcfc3b001f4fae5172b0e153f358171368526c212f8f5dffa68f
+oid sha256:5d6578a81728865849e42e6628772ec9d1e42fa52835b77cf7f6701c70eb964a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0304,
+  "epoch": 0.032,
   "eval_steps": 500,
-  "global_step": 380,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -140,6 +140,13 @@
       "learning_rate": 1.9e-05,
       "loss": 3.9827,
       "step": 380
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 26.463253021240234,
+      "learning_rate": 1.9999999999999998e-05,
+      "loss": 3.9454,
+      "step": 400
     }
   ],
   "logging_steps": 20,
@@ -147,7 +154,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 911840340049920.0,
+  "total_flos": 961410073952256.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null