Training in progress, step 1800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96c2643c948e8c26b7915122497df4ae83b2431b99ef269d2d4d0a8ef6631cdf
+oid sha256:1be781d2ff87c04388aa549d471acb1e75cc1efe382632ff5dc00d5c1ea625ec
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ea28045dbb6354fdb95725f985f2e38a5208180a9cae044b1a856afbe37f579
+oid sha256:6ad46c9cf2c24c36d0e90811f32a6a02d31aec3126bc1b48c2d510d7f257d952
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ca9c04f6b7646a0509be2acc7ecfafb1dcb2d23d1ea2918a0e476af152e1e5d
+oid sha256:0909f77b12ea1b25d87482885e6c2cc12d4e855bbbbb4a8ffcede021a58b61fd
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0410ad60e6d0138b921a03b0a3e367fd27c6ab07cb9a5006fcb66ea8e5bbacc4
+oid sha256:c0e0a1736a46fd1627af3c246e44261aaac909256abbd413b5ee5c968f6b2d8e
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3168717622756958,
-  "best_model_checkpoint": "./outputs/checkpoint-1700",
-  "epoch": 2.2666666666666666,
+  "best_metric": 1.3101677894592285,
+  "best_model_checkpoint": "./outputs/checkpoint-1800",
+  "epoch": 2.4,
   "eval_steps": 100,
-  "global_step": 1700,
+  "global_step": 1800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -245,6 +245,20 @@
       "eval_samples_per_second": 30.726,
       "eval_steps_per_second": 3.854,
       "step": 1700
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 0.0002,
+      "loss": 1.3862,
+      "step": 1800
+    },
+    {
+      "epoch": 2.4,
+      "eval_loss": 1.3101677894592285,
+      "eval_runtime": 47.1712,
+      "eval_samples_per_second": 30.76,
+      "eval_steps_per_second": 3.858,
+      "step": 1800
     }
   ],
   "logging_steps": 100,
@@ -252,7 +266,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 5.700115136249856e+16,
+  "total_flos": 6.035490006368256e+16,
   "trial_name": null,
   "trial_params": null
 }