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:b9c465310a918d62126a8beae4b466082097c340651ba34aace36864e68f2a23
+oid sha256:630f7e6aa1e3db589077f0429efa04846575e9dd58c9d5c5e6eb25645f4057cd
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4c0f6432a4513c631f42fc293c0200025a942e3bc8494e0d653314ef5c803a5
+oid sha256:796a198b5c521a08d467714419fdd29c618858cd611c533e8231b4dee4e2896c
 size 41459700

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": 0.025359668373567422,
+  "epoch": 0.03251239535072747,
   "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": 34.845,
       "eval_steps_per_second": 17.429,
       "step": 39
+    },
+    {
+      "epoch": 0.026009916280581972,
+      "grad_norm": 0.3025207817554474,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.2036,
+      "step": 40
+    },
+    {
+      "epoch": 0.02666016418759652,
+      "grad_norm": 0.3241982161998749,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 1.2358,
+      "step": 41
+    },
+    {
+      "epoch": 0.02731041209461107,
+      "grad_norm": 0.37644854187965393,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.2374,
+      "step": 42
+    },
+    {
+      "epoch": 0.027960660001625618,
+      "grad_norm": 0.32864895462989807,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 1.1828,
+      "step": 43
+    },
+    {
+      "epoch": 0.028610907908640168,
+      "grad_norm": 0.3057841956615448,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 1.0924,
+      "step": 44
+    },
+    {
+      "epoch": 0.029261155815654718,
+      "grad_norm": 0.30859678983688354,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.2563,
+      "step": 45
+    },
+    {
+      "epoch": 0.029911403722669268,
+      "grad_norm": 0.2911403775215149,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.1663,
+      "step": 46
+    },
+    {
+      "epoch": 0.030561651629683818,
+      "grad_norm": 0.2932097017765045,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 1.2638,
+      "step": 47
+    },
+    {
+      "epoch": 0.031211899536698368,
+      "grad_norm": 0.32970038056373596,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 1.2205,
+      "step": 48
+    },
+    {
+      "epoch": 0.031862147443712914,
+      "grad_norm": 0.3031351566314697,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 1.1235,
+      "step": 49
+    },
+    {
+      "epoch": 0.03251239535072747,
+      "grad_norm": 0.3202054500579834,
+      "learning_rate": 0.0,
+      "loss": 1.2213,
+      "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": 3.694388417711309e+16,
+  "total_flos": 4.696404144213197e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null