Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b20a79446e3d426cb413524af2d6f1e176aefb51e24fd4c69e2d47752b4ff0b
+oid sha256:882a50e5e91f4b63d9915a2a6520c7ea442a7fa04ea5eb6b5fcc8645afe3f39b
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0126c12a51a77361f2f6117c7d3a61641bebd6ef55e9a95b1ffe90791831a2f6
+oid sha256:b95f5fb01e0ff21188ad7599fd3d9d8941758d05afaa264c1089feeeff2d3e95
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11babdea246a4e24996953deb155282010c386374754f4f502873f43203aed39
+oid sha256:4f4738ee211f4f50b9ad38da261c4a2ad61f02566b527c754ac2d36d925fa919
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75c3c8ae7ddabeca3cb69703f6b35f00b9125a4c27b56ccba4ed0e4669bb5433
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.10551234359147785,
+  "epoch": 0.13527223537368954,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -60,6 +60,36 @@
       "eval_samples_per_second": 20.266,
       "eval_steps_per_second": 2.539,
       "step": 30
+    },
+    {
+      "epoch": 0.10821778829895164,
+      "grad_norm": 0.2325286716222763,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.1448,
+      "step": 40
+    },
+    {
+      "epoch": 0.10821778829895164,
+      "eval_loss": 0.1379784345626831,
+      "eval_runtime": 122.3352,
+      "eval_samples_per_second": 20.354,
+      "eval_steps_per_second": 2.55,
+      "step": 40
+    },
+    {
+      "epoch": 0.13527223537368954,
+      "grad_norm": 0.4119989573955536,
+      "learning_rate": 0.0,
+      "loss": 0.1376,
+      "step": 50
+    },
+    {
+      "epoch": 0.13527223537368954,
+      "eval_loss": 0.13759860396385193,
+      "eval_runtime": 122.3459,
+      "eval_samples_per_second": 20.352,
+      "eval_steps_per_second": 2.55,
+      "step": 50
     }
   ],
   "logging_steps": 10,
@@ -74,12 +104,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.016329476809687e+17,
+  "total_flos": 1.302986508730368e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null