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:f7af08bf38edc442cdd0dd11f9880fa53d98d85272f457e008eb5df69db493ac
+oid sha256:86a52d6f46f21f4dfc464c172c3afede1f5ea9d625b985afe81f872b9efcf3b2
 size 399632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b57d616a64a25c3bd7c36467954f487c89539382a48deedeb5b9def6f934fd66
+oid sha256:d6ee075ecb84840da4109651cbc132b97cb77e943f215cbea7a34ef89d1c5057
 size 531130

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b68d72e4453f3fb41267c49c417bbf1251e4c68afbf092a72f91cff4b3c02793
+oid sha256:5d34319ff3df364313deadc6fed2a87af4dbaa25121577034e823762746bfdd8
 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": 0.016095715856962737,
+  "epoch": 0.021460954475950318,
   "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": 293.62,
       "eval_steps_per_second": 146.81,
       "step": 150
+    },
+    {
+      "epoch": 0.017168763580760256,
+      "grad_norm": 8797.31640625,
+      "learning_rate": 0.0002,
+      "loss": 14.0072,
+      "step": 160
+    },
+    {
+      "epoch": 0.01824181130455777,
+      "grad_norm": 9056.8310546875,
+      "learning_rate": 0.0002,
+      "loss": 13.368,
+      "step": 170
+    },
+    {
+      "epoch": 0.019314859028355287,
+      "grad_norm": 7576.951171875,
+      "learning_rate": 0.0002,
+      "loss": 13.6952,
+      "step": 180
+    },
+    {
+      "epoch": 0.020387906752152803,
+      "grad_norm": 5631.87890625,
+      "learning_rate": 0.0002,
+      "loss": 12.4032,
+      "step": 190
+    },
+    {
+      "epoch": 0.021460954475950318,
+      "grad_norm": 7482.162109375,
+      "learning_rate": 0.0002,
+      "loss": 12.4731,
+      "step": 200
+    },
+    {
+      "epoch": 0.021460954475950318,
+      "eval_loss": 3.307003974914551,
+      "eval_runtime": 13.2546,
+      "eval_samples_per_second": 296.048,
+      "eval_steps_per_second": 148.024,
+      "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": 28485196185600.0,
+  "total_flos": 37980261580800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null