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:c2cb4a8d2c53f2209c735537a0541dcbf0be050aba82e0c6d277afe1c990e15e
+oid sha256:2a25f482ff07752ba09f4ee854d100aaeb2e3fccdc9008c7b160d9615a46babc
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a509d38afb6fa50e4687625b3d1e96974885bfb2eeb35b25c8af3da2d8621548
+oid sha256:4a3217ac421c0726ae8b3d8d1c4dfc41ce73d7fe3d4c120187666fcdfe6c65bd
 size 127788180

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc5c30c1cf463cc3ea11b4c9b8030d978ab257f017aced72e684581b78d346fd
+oid sha256:b288db6c0b9b9fdf2fe8fca499cb76c0dd5ed6aff44aa2855e971fbb201426e3
 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": 0.007428132815014732,
+  "epoch": 0.00990417708668631,
   "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": 19.078,
       "eval_steps_per_second": 9.539,
       "step": 150
+    },
+    {
+      "epoch": 0.007923341669349049,
+      "grad_norm": 2.854691505432129,
+      "learning_rate": 0.0002,
+      "loss": 1.4273,
+      "step": 160
+    },
+    {
+      "epoch": 0.008418550523683363,
+      "grad_norm": 2.409813642501831,
+      "learning_rate": 0.0002,
+      "loss": 1.2796,
+      "step": 170
+    },
+    {
+      "epoch": 0.008913759378017678,
+      "grad_norm": 3.510165214538574,
+      "learning_rate": 0.0002,
+      "loss": 1.6296,
+      "step": 180
+    },
+    {
+      "epoch": 0.009408968232351994,
+      "grad_norm": 1.9833729267120361,
+      "learning_rate": 0.0002,
+      "loss": 1.2934,
+      "step": 190
+    },
+    {
+      "epoch": 0.00990417708668631,
+      "grad_norm": 2.511721134185791,
+      "learning_rate": 0.0002,
+      "loss": 1.2297,
+      "step": 200
+    },
+    {
+      "epoch": 0.00990417708668631,
+      "eval_loss": 0.6799042820930481,
+      "eval_runtime": 223.0803,
+      "eval_samples_per_second": 19.06,
+      "eval_steps_per_second": 9.53,
+      "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": 2.380421136384e+16,
+  "total_flos": 3.173894848512e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null