Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b96cc48801807197a2869651b8b6bac6965a6454c197be1b6e0eead5bf4161e
+oid sha256:698ab20718cc10d9d6dd500e26c1af255955ecaaf7cd618b737f1f5c2f51ea4b
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbf2f281f1e048b1bd4bff6fbf771eb2f17c530c5424c2de57c18a8d27369f77
+oid sha256:5d67ab9c0de778ee91cb6782ba25854e65777cef0371c9e776ac393db195635e
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8f4cd27f1868d83f3fdb16d5d64a2f27bbe41bb0197aaa9a0bc2e9c7bbe9aa4
+oid sha256:d1aefd6b5cb7ab5293be3b57c5a81d7e2a62b44d9e7b6cc213897ed1dd28dec5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ea7ff16b0c30a914eb0d145e3fb06ff9027c6cd2408e766ce8a09accab89a4d
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.001295840352468576,
+  "epoch": 0.002591680704937152,
   "eval_steps": 500,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -182,6 +182,181 @@
       "learning_rate": 0.00010654031292301432,
       "loss": 2.3092,
       "step": 25
+    },
+    {
+      "epoch": 0.001347673966567319,
+      "grad_norm": 1.8183993101119995,
+      "learning_rate": 0.0001,
+      "loss": 2.2552,
+      "step": 26
+    },
+    {
+      "epoch": 0.001399507580666062,
+      "grad_norm": 1.5538502931594849,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 2.3462,
+      "step": 27
+    },
+    {
+      "epoch": 0.001451341194764805,
+      "grad_norm": 1.5595468282699585,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 2.3715,
+      "step": 28
+    },
+    {
+      "epoch": 0.001503174808863548,
+      "grad_norm": 2.1476974487304688,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 2.293,
+      "step": 29
+    },
+    {
+      "epoch": 0.0015550084229622911,
+      "grad_norm": 1.9469425678253174,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 2.3133,
+      "step": 30
+    },
+    {
+      "epoch": 0.0016068420370610342,
+      "grad_norm": 1.6128257513046265,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 2.2834,
+      "step": 31
+    },
+    {
+      "epoch": 0.0016586756511597772,
+      "grad_norm": 1.5214881896972656,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 2.5029,
+      "step": 32
+    },
+    {
+      "epoch": 0.0017105092652585203,
+      "grad_norm": 1.5626273155212402,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 2.4548,
+      "step": 33
+    },
+    {
+      "epoch": 0.001762342879357263,
+      "grad_norm": 1.8093630075454712,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 2.5801,
+      "step": 34
+    },
+    {
+      "epoch": 0.0018141764934560061,
+      "grad_norm": 1.7555335760116577,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 2.3909,
+      "step": 35
+    },
+    {
+      "epoch": 0.0018660101075547492,
+      "grad_norm": 1.7623857259750366,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 2.3654,
+      "step": 36
+    },
+    {
+      "epoch": 0.0019178437216534922,
+      "grad_norm": 1.8313246965408325,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 2.053,
+      "step": 37
+    },
+    {
+      "epoch": 0.0019696773357522354,
+      "grad_norm": 1.8312631845474243,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 2.2619,
+      "step": 38
+    },
+    {
+      "epoch": 0.0020215109498509785,
+      "grad_norm": 1.3328640460968018,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 2.2884,
+      "step": 39
+    },
+    {
+      "epoch": 0.0020733445639497215,
+      "grad_norm": 1.395845890045166,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 2.1892,
+      "step": 40
+    },
+    {
+      "epoch": 0.0021251781780484646,
+      "grad_norm": 1.6217460632324219,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 2.4114,
+      "step": 41
+    },
+    {
+      "epoch": 0.0021770117921472076,
+      "grad_norm": 1.482170581817627,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 2.3014,
+      "step": 42
+    },
+    {
+      "epoch": 0.0022288454062459506,
+      "grad_norm": 1.5318725109100342,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 2.3725,
+      "step": 43
+    },
+    {
+      "epoch": 0.0022806790203446937,
+      "grad_norm": 1.729251742362976,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 2.306,
+      "step": 44
+    },
+    {
+      "epoch": 0.0023325126344434367,
+      "grad_norm": 1.675718903541565,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 2.3207,
+      "step": 45
+    },
+    {
+      "epoch": 0.0023843462485421798,
+      "grad_norm": 1.5841999053955078,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 2.1703,
+      "step": 46
+    },
+    {
+      "epoch": 0.002436179862640923,
+      "grad_norm": 1.4216182231903076,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 2.2403,
+      "step": 47
+    },
+    {
+      "epoch": 0.002488013476739666,
+      "grad_norm": 1.5462912321090698,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 2.3091,
+      "step": 48
+    },
+    {
+      "epoch": 0.002539847090838409,
+      "grad_norm": 1.3521757125854492,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 2.4685,
+      "step": 49
+    },
+    {
+      "epoch": 0.002591680704937152,
+      "grad_norm": 1.295125961303711,
+      "learning_rate": 0.0,
+      "loss": 2.1998,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -196,12 +371,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.70943641780224e+16,
+  "total_flos": 7.41887283560448e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null