Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b1e5ae09b2358a7cec14ebf082c6791eb4b2371a0e0e0f881d1f2f7de4e2d1e
+oid sha256:fb6c964abf5fba0140ceef78a457ef9dfe0a415de4005d6a94f8fd924a6bd64d
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e72e98a3f824f25f6d07ecdaffef31b797d3c943bad0324510fdfec7d11d317
+oid sha256:047044002c973001efc88fe6ce5409d6cffd6161cefdb3f03647599e83769bcf
 size 202110330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc78e937af6df61002f0454d4a89f4506e44ed33ab12b2726e58d84741b9206e
+oid sha256:c44e8899c47c14a7d0146026435d39d38d840dca09700e7658aff4bc8f197c9b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46fa8207e86dee7d50b0ab12f1dd18c4426e8c65d06f97f8b2bd004a747e9cfa
+oid sha256:212837ccb433e5430b061dc107b19dc09e932e6cfb62a751187d0903b7b0d94e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.004700573469963335,
+  "epoch": 0.007050860204945004,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,189 @@
       "eval_samples_per_second": 29.22,
       "eval_steps_per_second": 14.61,
       "step": 50
+    },
+    {
+      "epoch": 0.004794584939362603,
+      "grad_norm": 3.4442198276519775,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.8815,
+      "step": 51
+    },
+    {
+      "epoch": 0.004888596408761869,
+      "grad_norm": 3.3648104667663574,
+      "learning_rate": 2.3135019582658802e-05,
+      "loss": 0.8969,
+      "step": 52
+    },
+    {
+      "epoch": 0.004982607878161136,
+      "grad_norm": 3.168910503387451,
+      "learning_rate": 2.132117818244771e-05,
+      "loss": 0.8597,
+      "step": 53
+    },
+    {
+      "epoch": 0.005076619347560402,
+      "grad_norm": 3.004520893096924,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.8053,
+      "step": 54
+    },
+    {
+      "epoch": 0.005170630816959669,
+      "grad_norm": 2.8128843307495117,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.8096,
+      "step": 55
+    },
+    {
+      "epoch": 0.005264642286358936,
+      "grad_norm": 2.4147465229034424,
+      "learning_rate": 1.622048961921699e-05,
+      "loss": 0.7316,
+      "step": 56
+    },
+    {
+      "epoch": 0.005358653755758202,
+      "grad_norm": 2.472194194793701,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.7932,
+      "step": 57
+    },
+    {
+      "epoch": 0.005452665225157469,
+      "grad_norm": 1.9689332246780396,
+      "learning_rate": 1.3136133159493802e-05,
+      "loss": 0.6655,
+      "step": 58
+    },
+    {
+      "epoch": 0.005546676694556736,
+      "grad_norm": 1.9256327152252197,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.6854,
+      "step": 59
+    },
+    {
+      "epoch": 0.005640688163956003,
+      "grad_norm": 1.5773730278015137,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.5794,
+      "step": 60
+    },
+    {
+      "epoch": 0.0057346996333552695,
+      "grad_norm": 1.4215878248214722,
+      "learning_rate": 9.042397785550405e-06,
+      "loss": 0.6325,
+      "step": 61
+    },
+    {
+      "epoch": 0.005828711102754536,
+      "grad_norm": 1.2316890954971313,
+      "learning_rate": 7.830427709355725e-06,
+      "loss": 0.5846,
+      "step": 62
+    },
+    {
+      "epoch": 0.005922722572153803,
+      "grad_norm": 1.1193468570709229,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.513,
+      "step": 63
+    },
+    {
+      "epoch": 0.006016734041553069,
+      "grad_norm": 1.1295101642608643,
+      "learning_rate": 5.649458341088915e-06,
+      "loss": 0.4793,
+      "step": 64
+    },
+    {
+      "epoch": 0.006110745510952336,
+      "grad_norm": 0.9580612778663635,
+      "learning_rate": 4.684610648167503e-06,
+      "loss": 0.5239,
+      "step": 65
+    },
+    {
+      "epoch": 0.0062047569803516025,
+      "grad_norm": 1.2913953065872192,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.4928,
+      "step": 66
+    },
+    {
+      "epoch": 0.00629876844975087,
+      "grad_norm": 1.0162431001663208,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.5664,
+      "step": 67
+    },
+    {
+      "epoch": 0.0063927799191501366,
+      "grad_norm": 0.7663949728012085,
+      "learning_rate": 2.314152462588659e-06,
+      "loss": 0.4712,
+      "step": 68
+    },
+    {
+      "epoch": 0.006486791388549403,
+      "grad_norm": 0.8022221922874451,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.4734,
+      "step": 69
+    },
+    {
+      "epoch": 0.00658080285794867,
+      "grad_norm": 0.9547379016876221,
+      "learning_rate": 1.1851996440033319e-06,
+      "loss": 0.5119,
+      "step": 70
+    },
+    {
+      "epoch": 0.006674814327347936,
+      "grad_norm": 0.7708539366722107,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.4543,
+      "step": 71
+    },
+    {
+      "epoch": 0.006768825796747203,
+      "grad_norm": 0.9734583497047424,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.5059,
+      "step": 72
+    },
+    {
+      "epoch": 0.0068628372661464696,
+      "grad_norm": 0.8569084405899048,
+      "learning_rate": 1.9026509541272275e-07,
+      "loss": 0.5209,
+      "step": 73
+    },
+    {
+      "epoch": 0.006956848735545736,
+      "grad_norm": 0.8591418266296387,
+      "learning_rate": 4.7588920907110094e-08,
+      "loss": 0.5359,
+      "step": 74
+    },
+    {
+      "epoch": 0.007050860204945004,
+      "grad_norm": 0.8256073594093323,
+      "learning_rate": 0.0,
+      "loss": 0.5314,
+      "step": 75
+    },
+    {
+      "epoch": 0.007050860204945004,
+      "eval_loss": 0.5117783546447754,
+      "eval_runtime": 306.801,
+      "eval_samples_per_second": 29.198,
+      "eval_steps_per_second": 14.599,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -395,12 +578,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.04177049010176e+16,
+  "total_flos": 1.56265573515264e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null