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:b7a4c48360db0a424ba40064c9a98b5b502e9ed80c8becc432de0063ed6fe09f
+oid sha256:f73973158fead5384f22e99f919a7bae3e1579100a7d2d5f3d37274b1c183940
 size 65309632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f969cd334be0c6b92a0640ffbbd990f5e6071b45a4ae2c0e485f87f7b806b47
+oid sha256:c6ac13a35ff72084f05b0b0c0b13296aab3ad25f5fa83d6a71afc4db9094a4db
 size 33424212

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb7f45275d46363b2d78df3e7bd6c16e132bd0be6adf07c72e2e1cddb95e1ea3
+oid sha256:9224310228cbaf0817f311fa85a30c8e6f6b96dda3f24aad6d5782d069f640d3
 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": 0.0441306266548985,
+  "epoch": 0.05884083553986467,
   "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": 21.029,
       "eval_steps_per_second": 10.514,
       "step": 150
+    },
+    {
+      "epoch": 0.047072668431891736,
+      "grad_norm": 4.155463695526123,
+      "learning_rate": 0.0002,
+      "loss": 5.4264,
+      "step": 160
+    },
+    {
+      "epoch": 0.05001471020888497,
+      "grad_norm": 6.154460430145264,
+      "learning_rate": 0.0002,
+      "loss": 4.9961,
+      "step": 170
+    },
+    {
+      "epoch": 0.0529567519858782,
+      "grad_norm": 5.550375938415527,
+      "learning_rate": 0.0002,
+      "loss": 5.2762,
+      "step": 180
+    },
+    {
+      "epoch": 0.055898793762871435,
+      "grad_norm": 3.526017189025879,
+      "learning_rate": 0.0002,
+      "loss": 5.1083,
+      "step": 190
+    },
+    {
+      "epoch": 0.05884083553986467,
+      "grad_norm": 3.517319917678833,
+      "learning_rate": 0.0002,
+      "loss": 4.3682,
+      "step": 200
+    },
+    {
+      "epoch": 0.05884083553986467,
+      "eval_loss": 1.215588092803955,
+      "eval_runtime": 68.1783,
+      "eval_samples_per_second": 21.004,
+      "eval_steps_per_second": 10.502,
+      "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": 4.852540946330419e+16,
+  "total_flos": 6.472775391825101e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null