Training in progress, step 1200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73313b510262ad6fea44d6fd7e8409e14258688517c9ad8ddc0e67f4ce0297a8
+oid sha256:382b240f9d1673407b68b093fbad91a0baff5d06d465f933ca68136c1ff0fe18
 size 6298560

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4da25717d54dee0040e6e451dabd847036f2e4eaa04ae109b780eaa5ad47668e
+oid sha256:5d4f81ff79ebfb2f522b13eb064a7487bf55b02343f8b37eccc1cce33f7ba689
 size 12611145

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d22dab64389d09c1c4ec2d92a550bda02dac3229ea8840496cfeb7ab245cba6f
+oid sha256:b5af4843563639e31994cfd1ddd0f7cdf98dd7ca1ff3693b235dde4ed21ecd00
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f5f3a2d7191245a70e1410d8951fd2f5c94b0b91f13bf39c3f76fe8aaf57fd4
+oid sha256:3d8d6be7898f87772ccbc5c732e900fe63a643c4595ce6af3d6bc6f811ba4b65
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2266021966934204,
-  "best_model_checkpoint": "./outputs/checkpoint-1100",
-  "epoch": 1.4666666666666668,
+  "best_metric": 1.2204071283340454,
+  "best_model_checkpoint": "./outputs/checkpoint-1200",
+  "epoch": 1.6,
   "eval_steps": 100,
-  "global_step": 1100,
+  "global_step": 1200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -161,6 +161,20 @@
       "eval_samples_per_second": 4.119,
       "eval_steps_per_second": 0.517,
       "step": 1100
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.0002,
+      "loss": 1.0027,
+      "step": 1200
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 1.2204071283340454,
+      "eval_runtime": 475.1214,
+      "eval_samples_per_second": 4.062,
+      "eval_steps_per_second": 0.509,
+      "step": 1200
     }
   ],
   "logging_steps": 100,
@@ -168,7 +182,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 3.660881250995405e+16,
+  "total_flos": 3.993638976897024e+16,
   "trial_name": null,
   "trial_params": null
 }