Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6035a7e1286766bc508caee2000b5228d2dfa63ed69852c86146d22e3afe5a6
+oid sha256:b32a284191ed8f815c1b4da52e9868d4c3943696062ce59f7e0359205975d164
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea8417123d60ffa7ee27b8293e1db7f0a69d5cf75d499da36db016a5062a4dce
+oid sha256:90596f2268fb6967f50a76510a580ab161ae1f2648e3462c0a9b8fe6dcd4dde8
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de6db8638e0b6fd3f6f36ba78993a7ce8b0894e9874a13631ac927eea254697d
+oid sha256:2705fc8a9a81a893e86cce42854cae0a2f426748be407200ccc891187073c380
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.007452703993884961,
+  "epoch": 0.009554748710108925,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -88,6 +88,43 @@
       "learning_rate": 3.086582838174551e-05,
       "loss": 2.0011,
       "step": 35
+    },
+    {
+      "epoch": 0.007643798968087139,
+      "grad_norm": 3.834752321243286,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.962,
+      "step": 40
+    },
+    {
+      "epoch": 0.007643798968087139,
+      "eval_loss": 1.8478115797042847,
+      "eval_runtime": 331.0655,
+      "eval_samples_per_second": 6.657,
+      "eval_steps_per_second": 3.329,
+      "step": 40
+    },
+    {
+      "epoch": 0.008599273839098032,
+      "grad_norm": 3.228943109512329,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.8409,
+      "step": 45
+    },
+    {
+      "epoch": 0.009554748710108925,
+      "grad_norm": 3.1936380863189697,
+      "learning_rate": 0.0,
+      "loss": 2.0557,
+      "step": 50
+    },
+    {
+      "epoch": 0.009554748710108925,
+      "eval_loss": 1.8387521505355835,
+      "eval_runtime": 330.8485,
+      "eval_samples_per_second": 6.662,
+      "eval_steps_per_second": 3.331,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -102,12 +139,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.1421059232301056e+16,
+  "total_flos": 1.4657796666556416e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null