Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56464e6eeecd422860b5c1c7a6ee0a730545cfc0a4d0c880acfbfe91753bda76
+oid sha256:3be2a7e5cd505bfbd11190634b1de18aaa4c1e6a1b602f8c72b2066ed6cf2905
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9b267d480d7c869f04a01d1a4c306014298da5fafb64ad739a2cd8d0c248ce0
+oid sha256:40d73ada5e9cd3e604a8c2c9a097be4404d2a3b5e144a96ad87f98b1e52dae9c
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d37ac6b9656c6d4d0f1750b5ab70f41b92b70d7acf3d07624919939bd0aae33
+oid sha256:966e72396d27334e2e13b4971164fe1c286b550777441fb55fa07a5c5d04ec62
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b489c13e2d776471e9a48162938854a24466ce6713df9c0fb59abd9a09fb226b
+oid sha256:ca9a25c72339c898b564e0c464a3f6fc75bbeec408008928b7ed05533156b98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5923000987166831,
+  "epoch": 0.7897334649555775,
   "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": 11.499,
       "eval_steps_per_second": 5.803,
       "step": 150
+    },
+    {
+      "epoch": 0.631786771964462,
+      "grad_norm": 0.335482656955719,
+      "learning_rate": 2.0055723659649904e-05,
+      "loss": 0.7052,
+      "step": 160
+    },
+    {
+      "epoch": 0.6712734452122409,
+      "grad_norm": 0.3157788813114166,
+      "learning_rate": 1.1454397434679021e-05,
+      "loss": 0.7612,
+      "step": 170
+    },
+    {
+      "epoch": 0.7107601184600197,
+      "grad_norm": 0.35480332374572754,
+      "learning_rate": 5.146355805285452e-06,
+      "loss": 0.8409,
+      "step": 180
+    },
+    {
+      "epoch": 0.7502467917077986,
+      "grad_norm": 0.5036816596984863,
+      "learning_rate": 1.2949737362087156e-06,
+      "loss": 0.792,
+      "step": 190
+    },
+    {
+      "epoch": 0.7897334649555775,
+      "grad_norm": 0.3984379470348358,
+      "learning_rate": 0.0,
+      "loss": 0.8132,
+      "step": 200
+    },
+    {
+      "epoch": 0.7897334649555775,
+      "eval_loss": 0.7477403879165649,
+      "eval_runtime": 9.3074,
+      "eval_samples_per_second": 11.496,
+      "eval_steps_per_second": 5.802,
+      "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": 9.007850871324672e+16,
+  "total_flos": 1.2023660345819136e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null