Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87cf31743e614965a50fedc4eb7254e261cc69cf7bdc4193d81cae3d82da8ffd
+oid sha256:e02732510269342d14c62181c1280a9f610eb3992a7342492e6255d8d2d07c9b
 size 25191576

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:784552a53470b749bfb0fdb382aa1fba33ed8ed2166d99b25d3b23f8502eacfe
+oid sha256:22ae8fcda2dea592fb87b1362f8af5d8bd1eda662f2df2118ec2b901891d7c63
 size 50444613

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1399d80939b4d27a777d1f87cb586e5a9acf0b7d01a6d85fd06934d47d7efe99
+oid sha256:92f35b713645b2f6fb9d57649d0c8c63bb1e7812311062435203302e19fb74ba
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:216f76b8039f833c337db298c81f13b12082d5fd4f9d866cecd34b2ca7550b37
+oid sha256:7aa2c8b84e17817e6a4dcba5955fca913e266fdcd47f5594a29933ebd4972a01
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0747358798980713,
-  "best_model_checkpoint": "./outputs/checkpoint-100",
-  "epoch": 0.13333333333333333,
+  "best_metric": 1.0527141094207764,
+  "best_model_checkpoint": "./outputs/checkpoint-200",
+  "epoch": 0.26666666666666666,
   "eval_steps": 100,
-  "global_step": 100,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -21,6 +21,20 @@
       "eval_samples_per_second": 5.445,
       "eval_steps_per_second": 0.683,
       "step": 100
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0002,
+      "loss": 0.9173,
+      "step": 200
+    },
+    {
+      "epoch": 0.27,
+      "eval_loss": 1.0527141094207764,
+      "eval_runtime": 353.1278,
+      "eval_samples_per_second": 5.465,
+      "eval_steps_per_second": 0.685,
+      "step": 200
     }
   ],
   "logging_steps": 100,
@@ -28,7 +42,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.8285532237070336e+16,
+  "total_flos": 5.648480752523674e+16,
   "trial_name": null,
   "trial_params": null
 }