Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f534e1d5ac72bbda965bd18ab2bc7b7e936f755f40d9beb526a5e2e6108e542
+oid sha256:b867b377938bfc48e13ae33fc412e1633d7057dcf99f68cdae86b38ea0fd553f
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f4cdcf57fe0789633a253b32d7b458c5bb4ee98c478501ff9a0a4237beecbf8
+oid sha256:4a693b6c31ae3cb7c4627d237be26e54358e9bacab23b79ffeda59b25eb9d540
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd360841730d1ff60c2ccaf8d91de12acdf3fc61094ed31857db38641962f792
+oid sha256:872aec646209d88dc74552b29ea1d28cf33d153ba2dc22c5bcb7fdc67e68506f
 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": 0.1330671989354624,
+  "epoch": 0.17742293191394987,
   "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": 21.537,
       "eval_steps_per_second": 10.791,
       "step": 150
+    },
+    {
+      "epoch": 0.14193834553115992,
+      "grad_norm": 0.6735680103302002,
+      "learning_rate": 0.0002,
+      "loss": 0.1514,
+      "step": 160
+    },
+    {
+      "epoch": 0.1508094921268574,
+      "grad_norm": 0.9459832906723022,
+      "learning_rate": 0.0002,
+      "loss": 0.1609,
+      "step": 170
+    },
+    {
+      "epoch": 0.1596806387225549,
+      "grad_norm": 0.8725154399871826,
+      "learning_rate": 0.0002,
+      "loss": 0.1617,
+      "step": 180
+    },
+    {
+      "epoch": 0.16855178531825238,
+      "grad_norm": 0.8067336082458496,
+      "learning_rate": 0.0002,
+      "loss": 0.1449,
+      "step": 190
+    },
+    {
+      "epoch": 0.17742293191394987,
+      "grad_norm": 1.0607802867889404,
+      "learning_rate": 0.0002,
+      "loss": 0.1553,
+      "step": 200
+    },
+    {
+      "epoch": 0.17742293191394987,
+      "eval_loss": 0.15468284487724304,
+      "eval_runtime": 22.0333,
+      "eval_samples_per_second": 21.558,
+      "eval_steps_per_second": 10.802,
+      "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": 4.203134753911603e+16,
+  "total_flos": 5.631923135604326e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null