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:cfd117b45dd7be8a2d260dcb6fbda93f8eeda8e441856d1493b92884f47168cb
+oid sha256:65a7518a240317d3821383a876b46ccdf0e6fa91b1dd29d2a4a417dd64bdfc8c
 size 108113968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48afe9a81c135b45bf08b4710b7f165644175fef1bf8e9e49009cdd65bde8d3e
+oid sha256:9938db94044764a649b235214fba903962c1a7e82be7d5925205f97c6bd0670b
 size 55549892

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ed7ca119b1bf30b84e2a47e7f17ceb2248570daa1816b394db964ee75ab45ca
+oid sha256:e3e115d25c1ff84a5ff5dbca07e0050062f21f6c5aff64f5892c6eb3567cb752
 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": 0.009777401166769872,
+  "epoch": 0.013036534889026497,
   "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": 19.36,
       "eval_steps_per_second": 9.68,
       "step": 150
+    },
+    {
+      "epoch": 0.010429227911221197,
+      "grad_norm": 1.0430855751037598,
+      "learning_rate": 0.0002,
+      "loss": 1.7549,
+      "step": 160
+    },
+    {
+      "epoch": 0.011081054655672521,
+      "grad_norm": 1.1361061334609985,
+      "learning_rate": 0.0002,
+      "loss": 1.6927,
+      "step": 170
+    },
+    {
+      "epoch": 0.011732881400123848,
+      "grad_norm": 0.9144191741943359,
+      "learning_rate": 0.0002,
+      "loss": 1.7662,
+      "step": 180
+    },
+    {
+      "epoch": 0.012384708144575172,
+      "grad_norm": 0.8297296762466431,
+      "learning_rate": 0.0002,
+      "loss": 1.7277,
+      "step": 190
+    },
+    {
+      "epoch": 0.013036534889026497,
+      "grad_norm": 1.0495644807815552,
+      "learning_rate": 0.0002,
+      "loss": 1.7698,
+      "step": 200
+    },
+    {
+      "epoch": 0.013036534889026497,
+      "eval_loss": 1.7259982824325562,
+      "eval_runtime": 333.5702,
+      "eval_samples_per_second": 19.366,
+      "eval_steps_per_second": 9.683,
+      "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": 3.3248776600682496e+16,
+  "total_flos": 4.386991357034496e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null