Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05d5e7678126d1a879f4ffa40be1c01a679c22fe582005a8973619f2557095e5
+oid sha256:5b32f7c5cad3db104b61d453f0f79e3101ab9397281f828b69fcc9c4e0edaf81
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b94a3895c1e6ccfc41429e94316ee871c7dc196191dd303084e2fa53f7b6642
+oid sha256:b0a74cd8900613c6df93c988dc058e07de8296b126ea503982ccb421db6a0437
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44627e3dbaee3655496addb0d6d4bce4a40debfebf6c6e10d21a0f2b7bfe9f1f
+oid sha256:165775a81706fc7cc54da9d57569ee0e4160913c84da2611c706e26a87dd876e
 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": 0.03445899379738112,
+  "epoch": 0.04594532506317482,
   "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": 14.864,
       "eval_steps_per_second": 7.436,
       "step": 150
+    },
+    {
+      "epoch": 0.036756260050539856,
+      "grad_norm": 3.476005792617798,
+      "learning_rate": 2.0055723659649904e-05,
+      "loss": 2.0839,
+      "step": 160
+    },
+    {
+      "epoch": 0.0390535263036986,
+      "grad_norm": 3.5214390754699707,
+      "learning_rate": 1.1454397434679021e-05,
+      "loss": 2.0835,
+      "step": 170
+    },
+    {
+      "epoch": 0.04135079255685734,
+      "grad_norm": 2.7603869438171387,
+      "learning_rate": 5.146355805285452e-06,
+      "loss": 1.9875,
+      "step": 180
+    },
+    {
+      "epoch": 0.04364805881001608,
+      "grad_norm": 3.715656042098999,
+      "learning_rate": 1.2949737362087156e-06,
+      "loss": 2.215,
+      "step": 190
+    },
+    {
+      "epoch": 0.04594532506317482,
+      "grad_norm": 3.595850706100464,
+      "learning_rate": 0.0,
+      "loss": 2.1326,
+      "step": 200
+    },
+    {
+      "epoch": 0.04594532506317482,
+      "eval_loss": 0.5398027896881104,
+      "eval_runtime": 123.2162,
+      "eval_samples_per_second": 14.876,
+      "eval_steps_per_second": 7.442,
+      "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": 5.14408582175785e+16,
+  "total_flos": 6.852938863057306e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null