Training in progress, step 2540, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6346a70cf6093679d4d5b93fd3421bc7a3e8ca9f233962b574cc1e605da07a63
+oid sha256:f909b9fc067fab552364fb1de3f6e34dba04079b0b596520d0be14f0aea8874e
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2970350d5affaa1384aa18b2fcabe3041d0121f55ef78024ff71924e2b9bd97d
+oid sha256:ef69499f4fb45b90f7ff201ee61e0a27e72a0d41576fc428f11b0b3210d7edf5
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9eccae15e2cae4c77b5aefc4760075dc2fa9e695d63c8bcac7425551f60d749f
+oid sha256:c7cbc060d6be543690e84079f5a0f9038405e71cf9fd3cec769843460f91c90a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a5c37c503fee750e3269106b2ec8e747f83501e7f65e6d8e35bc17a08fbb85e
+oid sha256:3a4fa0a4cb65f7c841c287b50ca6fd51005d2271eb35681bcb90491c2c7baba1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9016100178890877,
+  "epoch": 0.9087656529516994,
   "eval_steps": 500,
-  "global_step": 2520,
+  "global_step": 2540,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2023,14 +2023,30 @@
       "loss": 0.3857,
       "num_input_tokens_seen": 1707744,
       "step": 2520
+    },
+    {
+      "epoch": 0.9051878354203936,
+      "grad_norm": 0.3340027332305908,
+      "learning_rate": 1.8962432915921287e-05,
+      "loss": 0.3598,
+      "num_input_tokens_seen": 1713524,
+      "step": 2530
+    },
+    {
+      "epoch": 0.9087656529516994,
+      "grad_norm": 0.29041382670402527,
+      "learning_rate": 1.8246869409660107e-05,
+      "loss": 0.3874,
+      "num_input_tokens_seen": 1720278,
+      "step": 2540
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 1707744,
+  "num_input_tokens_seen": 1720278,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 3.840113184650035e+16,
+  "total_flos": 3.868297724403302e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null