Training in progress, step 1700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9dab9bda75617893936d1029f5198f90eb16acd337ae685b3ae1785d29eb3377
+oid sha256:5194638e012d2e383076ad139be88fe11b1a207de27a2e328c42de9948c6eaa0
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:609895c2334e5b0ede08844fc13fb79f5340a2efde198c292f0c91f33afee687
+oid sha256:05dae03fa651ff4f45c61e157e3bd83eda35192b500535c86ac1503044a601ec
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:447f4e5e01c0be926e916558e05968f8dccd3ae815e436a13fca4d71927a76d5
+oid sha256:cbb111828d85f47f912262c44e084ad812e1b819e6449de4a16205c7fe52ef94
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcd2587f362188ac4728d4fa6edf8d2b0b6d72db365d49f7b847d4d79e3da09f
+oid sha256:0410ad60e6d0138b921a03b0a3e367fd27c6ab07cb9a5006fcb66ea8e5bbacc4
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.307134985923767,
-  "best_model_checkpoint": "./outputs/checkpoint-1600",
-  "epoch": 2.1333333333333333,
+  "best_metric": 1.3011658191680908,
+  "best_model_checkpoint": "./outputs/checkpoint-1700",
+  "epoch": 2.2666666666666666,
   "eval_steps": 100,
-  "global_step": 1600,
+  "global_step": 1700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -231,6 +231,20 @@
       "eval_samples_per_second": 12.725,
       "eval_steps_per_second": 1.596,
       "step": 1600
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 0.0002,
+      "loss": 1.0507,
+      "step": 1700
+    },
+    {
+      "epoch": 2.27,
+      "eval_loss": 1.3011658191680908,
+      "eval_runtime": 151.5927,
+      "eval_samples_per_second": 12.731,
+      "eval_steps_per_second": 1.596,
+      "step": 1700
     }
   ],
   "logging_steps": 100,
@@ -238,7 +252,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.0197592855252992e+17,
+  "total_flos": 1.0835407735197696e+17,
   "trial_name": null,
   "trial_params": null
 }