Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62cad1900e5ab5f9cf7a434864d5e34e9e15b6ba1d7f44608590b27fc1d902e2
+oid sha256:0a1cd7b24fa6a3557e3c9c1f8f95040ad2b4139e4c0265075ce2812556e2d18b
 size 156926880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:030d09393d6feba96439d5f7a7ebf9d2c003756aefa441ba9bd045d6616b6af9
+oid sha256:e41109a5bde9b84f1a44d2d9d543a7bf2690cb2b7bb03cab3bd829a542a12c3a
 size 79968772

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28cb1b5e093b2599d8fa1806646d1f09bc9ce7ac92f9796c6863470342508537
+oid sha256:1842e55417742168b8bd9b1516cf24155d20a6818e0bf2f1d963bcf713e15763
 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": 0.19775873434410018,
+  "epoch": 0.26367831245880025,
   "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": 36.638,
       "eval_steps_per_second": 18.319,
       "step": 150
+    },
+    {
+      "epoch": 0.2109426499670402,
+      "grad_norm": 2.055669069290161,
+      "learning_rate": 2.0055723659649904e-05,
+      "loss": 1.195,
+      "step": 160
+    },
+    {
+      "epoch": 0.22412656558998023,
+      "grad_norm": 1.9988248348236084,
+      "learning_rate": 1.1454397434679021e-05,
+      "loss": 1.2536,
+      "step": 170
+    },
+    {
+      "epoch": 0.23731048121292023,
+      "grad_norm": 1.9996018409729004,
+      "learning_rate": 5.146355805285452e-06,
+      "loss": 1.2251,
+      "step": 180
+    },
+    {
+      "epoch": 0.2504943968358603,
+      "grad_norm": 1.882158637046814,
+      "learning_rate": 1.2949737362087156e-06,
+      "loss": 1.1557,
+      "step": 190
+    },
+    {
+      "epoch": 0.26367831245880025,
+      "grad_norm": 1.6782889366149902,
+      "learning_rate": 0.0,
+      "loss": 1.2426,
+      "step": 200
+    },
+    {
+      "epoch": 0.26367831245880025,
+      "eval_loss": 1.1376292705535889,
+      "eval_runtime": 4.3608,
+      "eval_samples_per_second": 36.69,
+      "eval_steps_per_second": 18.345,
+      "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": 7450611469516800.0,
+  "total_flos": 9934148626022400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null