Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:831e0bb05b9a1f36b45a9a19c3eecd1dc0fb1c2969369ba1ed34980e9fac859a
+oid sha256:e08e739dfe9ce7a6b1ceea6e42d1bdad45e2fe71584162c058377ef279a58eab
 size 9443384

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:620eff553fb45535fa832e5821e526b46bdef98bb70af4a85cd0f8aaa5d67da4
+oid sha256:1f169b79530e61ae7689d39ba804d5d85e54f495402fa5f685977d7ac56e2649
 size 18915130

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7335e8cb289a1ea0e43c1def6041371603222b00ab32f88b9848447ef726d6c
+oid sha256:4ad978cca8e8c4322b29aa3e0a4609c75d2569be4addeebd03d3b57f8afb1187
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb8b0b45d9468b388201df4849fd7d961d84a89385733d7db18055480fb25ddf
+oid sha256:6c0d912a292bbdd68cfb4f0c80a88e4888079a5e3307ae09473cfae396375942
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0012910305651486298,
+  "epoch": 0.0025820611302972596,
   "eval_steps": 500,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -67,6 +67,66 @@
       "learning_rate": 1.8e-06,
       "loss": 9.1707,
       "step": 10
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 10.1454,
+      "step": 11
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.2e-06,
+      "loss": 9.3448,
+      "step": 12
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 9.7101,
+      "step": 13
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.6e-06,
+      "loss": 9.9546,
+      "step": 14
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.8000000000000003e-06,
+      "loss": 9.6989,
+      "step": 15
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 3e-06,
+      "loss": 9.6937,
+      "step": 16
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 3.2000000000000003e-06,
+      "loss": 9.5372,
+      "step": 17
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 3.4000000000000005e-06,
+      "loss": 9.1956,
+      "step": 18
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 3.6e-06,
+      "loss": 9.7139,
+      "step": 19
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 3.8e-06,
+      "loss": 9.5589,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -74,7 +134,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 10,
-  "total_flos": 13280654057472.0,
+  "total_flos": 26086414196736.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null