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:cc1ca0ccaf04e66ac626c3560a422be72f364dd63c17c9cc9341ae76d27aaae7
+oid sha256:faff83e44deed5039e6067bb9f4ecbf6eb6c34a9459c21c7ff9a5d91507c85c5
 size 59933632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc49ecc5da5dd9bf5ee144ea9e35e23ef3f716ab9a2018ae806b69df63440b13
+oid sha256:70166cbff0ba3d78017fbe4953829613d65f93e50a1665c5a15e038649913841
 size 31822948

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:652365ff63294ffff01ffedb52e831cc2560ab06b5699bca21d63e81dd0efbe7
+oid sha256:2edc13c60910e9acd555e90579b2ee1807926bb393c7c79b1e24163c3f5bfc9f
 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": 0.002365455255366816,
+  "epoch": 0.0030326349427779696,
   "eval_steps": 13,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -312,6 +312,83 @@
       "eval_samples_per_second": 62.546,
       "eval_steps_per_second": 31.274,
       "step": 39
+    },
+    {
+      "epoch": 0.0024261079542223754,
+      "grad_norm": 4.615245342254639,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 4.0557,
+      "step": 40
+    },
+    {
+      "epoch": 0.002486760653077935,
+      "grad_norm": 4.661611557006836,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 3.9913,
+      "step": 41
+    },
+    {
+      "epoch": 0.002547413351933494,
+      "grad_norm": 5.690472602844238,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 4.248,
+      "step": 42
+    },
+    {
+      "epoch": 0.0026080660507890535,
+      "grad_norm": 3.9581613540649414,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 4.0683,
+      "step": 43
+    },
+    {
+      "epoch": 0.002668718749644613,
+      "grad_norm": 4.146228790283203,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 4.1314,
+      "step": 44
+    },
+    {
+      "epoch": 0.0027293714485001723,
+      "grad_norm": 3.5570755004882812,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 4.22,
+      "step": 45
+    },
+    {
+      "epoch": 0.0027900241473557317,
+      "grad_norm": 4.9019927978515625,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 4.2201,
+      "step": 46
+    },
+    {
+      "epoch": 0.002850676846211291,
+      "grad_norm": 5.012303829193115,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 3.8878,
+      "step": 47
+    },
+    {
+      "epoch": 0.002911329545066851,
+      "grad_norm": 4.317418098449707,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 4.354,
+      "step": 48
+    },
+    {
+      "epoch": 0.0029719822439224102,
+      "grad_norm": 3.3168728351593018,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 3.8045,
+      "step": 49
+    },
+    {
+      "epoch": 0.0030326349427779696,
+      "grad_norm": 3.926177978515625,
+      "learning_rate": 0.0,
+      "loss": 4.1879,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -326,12 +403,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.0695463523057664e+16,
+  "total_flos": 1.37121327218688e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null