Training in progress, step 1100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd75f7f0c621d49adbe491567287289c483b65e7b1d0f2175e9a45b56cce6cf1
+oid sha256:73313b510262ad6fea44d6fd7e8409e14258688517c9ad8ddc0e67f4ce0297a8
 size 6298560

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6984629938fc6f9e73a00b81ad84a883f39c33f4dcfc7436bd5d3d0f8a58e63
+oid sha256:4da25717d54dee0040e6e451dabd847036f2e4eaa04ae109b780eaa5ad47668e
 size 12611145

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4f9ebefd315b6aa0431f975c131196c12b6ed3814a868d8dd6b6b3aee982673
+oid sha256:d22dab64389d09c1c4ec2d92a550bda02dac3229ea8840496cfeb7ab245cba6f
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bb7339d1d2da342a44f3ba5e076fb6e5d93aee86f890c002703d2b3a0750820
+oid sha256:1f5f3a2d7191245a70e1410d8951fd2f5c94b0b91f13bf39c3f76fe8aaf57fd4
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.232779622077942,
-  "best_model_checkpoint": "./outputs/checkpoint-1000",
-  "epoch": 1.3333333333333333,
+  "best_metric": 1.2266021966934204,
+  "best_model_checkpoint": "./outputs/checkpoint-1100",
+  "epoch": 1.4666666666666668,
   "eval_steps": 100,
-  "global_step": 1000,
+  "global_step": 1100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -147,6 +147,20 @@
       "eval_samples_per_second": 4.079,
       "eval_steps_per_second": 0.511,
       "step": 1000
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.0002,
+      "loss": 1.0152,
+      "step": 1100
+    },
+    {
+      "epoch": 1.47,
+      "eval_loss": 1.2266021966934204,
+      "eval_runtime": 468.5166,
+      "eval_samples_per_second": 4.119,
+      "eval_steps_per_second": 0.517,
+      "step": 1100
     }
   ],
   "logging_steps": 100,
@@ -154,7 +168,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 3.3290074696679424e+16,
+  "total_flos": 3.660881250995405e+16,
   "trial_name": null,
   "trial_params": null
 }