Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5df1895fe203f64df8e02891949e0d4f3b91bd69347af25cabcd5f31b9dbb7a3
+oid sha256:5674c279ccc1a14ad7d2cf6a3c58cd89fc2efcc58550ac2132c788689968d701
 size 161714

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84de0af83dd35cbcfb9a68c6080caa171a874eea44b0b921160b16a4a440f166
+oid sha256:13feb884f1e220a5ddc6fd7a25173fee504ae82355276f5357b6957b7772c249
 size 64750

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e2ccc87bbc2067b1c7dbaa62c69a78674f65e3be9822a7c1eb1394666e24257
+oid sha256:48b5f447fdf5275d96a8aa3fd1a386234c8c0b0a0ddf0d4ee97f8353919167c5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd5d42bb0afda20ec4c83d38c6af1131541c335ecab229c74e7f418894f3c13b
+oid sha256:ca9a25c72339c898b564e0c464a3f6fc75bbeec408008928b7ed05533156b98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.02829121086382497,
+  "epoch": 0.03772161448509996,
   "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": 460.973,
       "eval_steps_per_second": 230.59,
       "step": 150
+    },
+    {
+      "epoch": 0.03017729158807997,
+      "grad_norm": 0.07248049229383469,
+      "learning_rate": 2.1085949060360654e-05,
+      "loss": 6.8913,
+      "step": 160
+    },
+    {
+      "epoch": 0.03206337231233497,
+      "grad_norm": 0.0830499455332756,
+      "learning_rate": 1.2052624879351104e-05,
+      "loss": 6.8887,
+      "step": 170
+    },
+    {
+      "epoch": 0.033949453036589965,
+      "grad_norm": 0.07756847143173218,
+      "learning_rate": 5.418275829936537e-06,
+      "loss": 6.8908,
+      "step": 180
+    },
+    {
+      "epoch": 0.035835533760844966,
+      "grad_norm": 0.0987529531121254,
+      "learning_rate": 1.3638696597277679e-06,
+      "loss": 6.8915,
+      "step": 190
+    },
+    {
+      "epoch": 0.03772161448509996,
+      "grad_norm": 0.08450785279273987,
+      "learning_rate": 0.0,
+      "loss": 6.8897,
+      "step": 200
+    },
+    {
+      "epoch": 0.03772161448509996,
+      "eval_loss": 6.891111373901367,
+      "eval_runtime": 4.8186,
+      "eval_samples_per_second": 463.411,
+      "eval_steps_per_second": 231.809,
+      "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": 249823604736.0,
+  "total_flos": 332548835328.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null