Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fc4fd4c786a85ca3a196e03033cfd27ffbe6d49f091667f6f31b7384d2df44c
+oid sha256:1fcb1aab3792e7d42c01579c678598c7012df53d7d426713e8f7da7dfdb39b0e
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:189a671a69fb5c6163f5edefeb886dbc3f6552f92137887b6bf92229b11a3658
+oid sha256:34a71c49abe844d374927b794fad47aba66652523f4de2a1a7ad2b4a9ab5a29c
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b58650bd0af9f9dcea9f0f97784c48ee7e253296f93b2228f5405c1d5b3c7785
+oid sha256:6e7c3b659fbeea5fd1ec5c45b53988f97ee9e93acdf33965021f9614315337b9
 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": 0.0097085807673015,
+  "epoch": 0.012944774356402,
   "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": 33.394,
       "eval_steps_per_second": 16.697,
       "step": 150
+    },
+    {
+      "epoch": 0.0103558194851216,
+      "grad_norm": 0.8797596096992493,
+      "learning_rate": 0.0002,
+      "loss": 1.1071,
+      "step": 160
+    },
+    {
+      "epoch": 0.0110030582029417,
+      "grad_norm": 0.90439373254776,
+      "learning_rate": 0.0002,
+      "loss": 1.0443,
+      "step": 170
+    },
+    {
+      "epoch": 0.0116502969207618,
+      "grad_norm": 1.0083608627319336,
+      "learning_rate": 0.0002,
+      "loss": 1.0347,
+      "step": 180
+    },
+    {
+      "epoch": 0.0122975356385819,
+      "grad_norm": 0.8776618838310242,
+      "learning_rate": 0.0002,
+      "loss": 0.9837,
+      "step": 190
+    },
+    {
+      "epoch": 0.012944774356402,
+      "grad_norm": 0.9423546195030212,
+      "learning_rate": 0.0002,
+      "loss": 1.048,
+      "step": 200
+    },
+    {
+      "epoch": 0.012944774356402,
+      "eval_loss": 0.9568792581558228,
+      "eval_runtime": 195.0298,
+      "eval_samples_per_second": 33.359,
+      "eval_steps_per_second": 16.68,
+      "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": 2.8056440342052864e+16,
+  "total_flos": 3.751024089209242e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null