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:fe13648a5b8713e7f3cfc820b18daa7340f9353a5a22f1623e9ec3e132f5ddf2
+oid sha256:b6b50f3a2d925e32ae6bc6869a33eaae34106caa7e6aa476131bcb9f20b77ba1
 size 12609416

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff4376c9a1f1017780ba74faf6bf604fd2d6a6eda4e6f5b352e2b719d978f8f4
+oid sha256:548936d1046f745830639833eff4b84be92c66fb564df9b87fedbd874de2f4bf
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7756e62ba93d3ad8fc56f792a0fa0e7bf49c9acc70f3a6bafabd269c84b25668
+oid sha256:c6ce0496bb17b87a1eb1d4d4c4aba44498f3bc49999fb01c7c862faa769fecdc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b489c13e2d776471e9a48162938854a24466ce6713df9c0fb59abd9a09fb226b
+oid sha256:ca9a25c72339c898b564e0c464a3f6fc75bbeec408008928b7ed05533156b98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03305238803503553,
+  "epoch": 0.04406985071338071,
   "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": 70.104,
       "eval_steps_per_second": 35.07,
       "step": 150
+    },
+    {
+      "epoch": 0.03525588057070456,
+      "grad_norm": 4.137444972991943,
+      "learning_rate": 2.0055723659649904e-05,
+      "loss": 8.1067,
+      "step": 160
+    },
+    {
+      "epoch": 0.0374593731063736,
+      "grad_norm": 6.9792094230651855,
+      "learning_rate": 1.1454397434679021e-05,
+      "loss": 8.0706,
+      "step": 170
+    },
+    {
+      "epoch": 0.03966286564204264,
+      "grad_norm": 4.64994478225708,
+      "learning_rate": 5.146355805285452e-06,
+      "loss": 8.0563,
+      "step": 180
+    },
+    {
+      "epoch": 0.04186635817771167,
+      "grad_norm": 3.8868253231048584,
+      "learning_rate": 1.2949737362087156e-06,
+      "loss": 8.1085,
+      "step": 190
+    },
+    {
+      "epoch": 0.04406985071338071,
+      "grad_norm": 3.856034517288208,
+      "learning_rate": 0.0,
+      "loss": 8.0026,
+      "step": 200
+    },
+    {
+      "epoch": 0.04406985071338071,
+      "eval_loss": 1.9883368015289307,
+      "eval_runtime": 27.2971,
+      "eval_samples_per_second": 70.008,
+      "eval_steps_per_second": 35.022,
+      "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": 1291198031462400.0,
+  "total_flos": 1715341570867200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null