Training in progress, step 900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64fdbe98ea9ff1aaa3934406d079f6e9f6edfb8b0f995ab001a7a5996589a6a8
+oid sha256:da7e409316683c633c0ae53d8d67eb49145a0d2c9bfe79abcdeef58aa19562fb
 size 12595704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef8f119f447683c354fd7c289dd1b1e4d72a72bc752770a750352926a8472a43
+oid sha256:249e5cd20467754aeb0d0ee97b688c834839dd65fa0b6cf8e70e957b74737f30
 size 25222341

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97f421960082621eb5d18a65ca61753285f8400dd4a46495b865c4b2f5f1806c
+oid sha256:78e602e0905f2f4cd3eaf79c0118d57897fc5559f4a434cf3e4f71108013ea94
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de7840bcb72f2f480fd301578d289cdfa174589e831b0d33e5772f3956b6beae
+oid sha256:a3c39113390004215769b6e7fbe73f1073dd2faa3ab8f9ff815b62e9c2f80c82
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.103180170059204,
-  "best_model_checkpoint": "./outputs/checkpoint-800",
-  "epoch": 1.0666666666666667,
+  "best_metric": 1.1001368761062622,
+  "best_model_checkpoint": "./outputs/checkpoint-900",
+  "epoch": 1.2,
   "eval_steps": 100,
-  "global_step": 800,
+  "global_step": 900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -119,6 +119,20 @@
       "eval_samples_per_second": 3.629,
       "eval_steps_per_second": 0.455,
       "step": 800
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0002,
+      "loss": 0.9517,
+      "step": 900
+    },
+    {
+      "epoch": 1.2,
+      "eval_loss": 1.1001368761062622,
+      "eval_runtime": 467.265,
+      "eval_samples_per_second": 4.13,
+      "eval_steps_per_second": 0.518,
+      "step": 900
     }
   ],
   "logging_steps": 100,
@@ -126,7 +140,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.130969014206382e+17,
+  "total_flos": 1.2719281132194202e+17,
   "trial_name": null,
   "trial_params": null
 }