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:bc79153f372e3455b3410cb33a843a82bfe2f5f50eba9b775b6a39543b9c1e23
+oid sha256:26b8ab02d4c51652a297cd921a8b8e75ee87da0c6dd6759026883d5ac6d600cc
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:228f579833aa14f06dfdc951d2784c1190082bfcea7fbf94d13ae9ce64c2ad85
+oid sha256:3b5d4fb7b810b3b798da835135ac1d3f9a3a98527bfe6f5824a2e8eb892b7928
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:346a86e33c4fc9bb13ea2c6d8957c569c6b0f0d7f2f487067bbdfae3040ed41d
+oid sha256:ed283f2fd3cfa40c754e8a52d5a633214a74755f09dc2d6728899903b8c976a5
 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": 0.004562871098891456,
+  "epoch": 0.005849834742168534,
   "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": 5.6131,
       "step": 35
+    },
+    {
+      "epoch": 0.004679867793734827,
+      "grad_norm": 12.215734481811523,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 5.6891,
+      "step": 40
+    },
+    {
+      "epoch": 0.004679867793734827,
+      "eval_loss": 1.4018374681472778,
+      "eval_runtime": 725.6503,
+      "eval_samples_per_second": 4.96,
+      "eval_steps_per_second": 2.481,
+      "step": 40
+    },
+    {
+      "epoch": 0.00526485126795168,
+      "grad_norm": 7.4448161125183105,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 5.3698,
+      "step": 45
+    },
+    {
+      "epoch": 0.005849834742168534,
+      "grad_norm": 11.222515106201172,
+      "learning_rate": 0.0,
+      "loss": 5.4539,
+      "step": 50
+    },
+    {
+      "epoch": 0.005849834742168534,
+      "eval_loss": 1.3965027332305908,
+      "eval_runtime": 730.5266,
+      "eval_samples_per_second": 4.927,
+      "eval_steps_per_second": 2.464,
+      "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": 7317404761718784.0,
+  "total_flos": 9245343740854272.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null