Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25a8b5861b88c98f2d0644df3e89a5824209a13e4dfd80d9e805bbe1e2f03d1f
+oid sha256:73a64d212d91714ae7edef5a1ab5c06b2d5ed812b0e25b4522e2b0708c793310
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cc2cf51b4a5059c5a7859ee786d8a22458a4bf4142848037f947d6488e4e9a5
+oid sha256:d583887bad79b7fb9279741d32c7abb2ec2b20b479ce29beb9ccccca18fffa3d
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4657ed5dc8f18f92b9c19e106cbb47a5d3654d9de41fb19730a5634e589e2b00
+oid sha256:1a1d217403fa1139e029289c543d2ed96413d9c6c137ba7597b58856b01693e1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d31dc31a119769737d72f3df4c8cdf99522596cafc12bf2eea05a4ff374f599c
+oid sha256:859ff0676471245c9481ca25d6d6778d1c7963c39b7877af46bb8ca30a9ead21
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.003018700851776757,
+  "epoch": 0.004024934469035676,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 24.367,
       "eval_steps_per_second": 12.184,
       "step": 150
+    },
+    {
+      "epoch": 0.003219947575228541,
+      "grad_norm": 1.3226466178894043,
+      "learning_rate": 0.0002,
+      "loss": 1.3085,
+      "step": 160
+    },
+    {
+      "epoch": 0.0034211942986803246,
+      "grad_norm": 1.9192092418670654,
+      "learning_rate": 0.0002,
+      "loss": 1.1933,
+      "step": 170
+    },
+    {
+      "epoch": 0.0036224410221321083,
+      "grad_norm": 1.0368775129318237,
+      "learning_rate": 0.0002,
+      "loss": 1.2231,
+      "step": 180
+    },
+    {
+      "epoch": 0.003823687745583892,
+      "grad_norm": 1.5248116254806519,
+      "learning_rate": 0.0002,
+      "loss": 1.2734,
+      "step": 190
+    },
+    {
+      "epoch": 0.004024934469035676,
+      "grad_norm": 0.9554014801979065,
+      "learning_rate": 0.0002,
+      "loss": 1.1498,
+      "step": 200
+    },
+    {
+      "epoch": 0.004024934469035676,
+      "eval_loss": 1.397660255432129,
+      "eval_runtime": 858.6574,
+      "eval_samples_per_second": 24.367,
+      "eval_steps_per_second": 12.184,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -158,12 +201,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.48774183469056e+16,
+  "total_flos": 4.68217396985856e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null