Training in progress, step 160, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1beb7f2e0502feb6586b3268e2aa339af5bb5b1aecdba28220efe9b86e05aab
+oid sha256:21a16ada83dd7dd5808e0d99a2ec5aa1114c1c07cd5c4f3dddb21e922b6ee942
 size 183784

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22bcbbecdb02b3cbb28f48bb4653f48180a818d709bea369f228efcf4523d050
+oid sha256:4fd50731d2a5a8be56996530ea3d782beb43a0d77357b6a36a364568ea861968
 size 236760

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bb812854271d2dd6f5d1621a16e346cd2a930ab781f162177c7455f20c7291c
+oid sha256:7009543aa37573e0ccc837cbe37a5ee87ba344f4aab540963764e8d4b19f204e
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bf0f7c6ecc3ac28466ea76bb6b708b78e42abd3fbd5d001417b73e948d81162
+oid sha256:7763bb8f377954e0bddc1d7ce2e55ec5a4ed3c6dbf3e87a73b7b45be1b822940
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d159cb47b8d829628c4baba13b9b0791bfd74ecb5fa0e98be732c166ae850c2f
+oid sha256:7ac129e41885f14dee9f6f1a7ab9fe677a3b8903c8bd655d256be1058eb79064
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c040133306db04c9d19ef87920c336e46502a4a93e9907439fe79475367d13b
+oid sha256:741346a2e1b666efe4264bb863a2e0db43e713447d64294602148488119ce476
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3400db4ad22089f92d8cb2575defb82bd326765413235c180f06a5c672c23bc
+oid sha256:05806cda9d302d71418674ceed0403c9c434840aa85440a19eee03178d2621d8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.137931034482759,
+  "epoch": 5.517241379310345,
   "eval_steps": 16,
-  "global_step": 120,
+  "global_step": 160,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -155,6 +155,58 @@
       "learning_rate": 1.6135921418712956e-05,
       "loss": 11.9174,
       "step": 120
+    },
+    {
+      "epoch": 4.413793103448276,
+      "eval_loss": 11.914271354675293,
+      "eval_runtime": 0.8796,
+      "eval_samples_per_second": 171.676,
+      "eval_steps_per_second": 6.822,
+      "step": 128
+    },
+    {
+      "epoch": 4.482758620689655,
+      "grad_norm": 0.025010688230395317,
+      "learning_rate": 9.307564136490254e-06,
+      "loss": 11.9173,
+      "step": 130
+    },
+    {
+      "epoch": 4.827586206896552,
+      "grad_norm": 0.025940613821148872,
+      "learning_rate": 4.2113336672471245e-06,
+      "loss": 11.917,
+      "step": 140
+    },
+    {
+      "epoch": 4.9655172413793105,
+      "eval_loss": 11.914034843444824,
+      "eval_runtime": 0.8301,
+      "eval_samples_per_second": 181.898,
+      "eval_steps_per_second": 7.228,
+      "step": 144
+    },
+    {
+      "epoch": 5.172413793103448,
+      "grad_norm": 0.020017573609948158,
+      "learning_rate": 1.064157733632276e-06,
+      "loss": 11.9172,
+      "step": 150
+    },
+    {
+      "epoch": 5.517241379310345,
+      "grad_norm": 0.02289649285376072,
+      "learning_rate": 0.0,
+      "loss": 11.9169,
+      "step": 160
+    },
+    {
+      "epoch": 5.517241379310345,
+      "eval_loss": 11.914515495300293,
+      "eval_runtime": 0.8607,
+      "eval_samples_per_second": 175.434,
+      "eval_steps_per_second": 6.971,
+      "step": 160
     }
   ],
   "logging_steps": 10,
@@ -169,12 +221,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1942502768640.0,
+  "total_flos": 2590003691520.0,
   "train_batch_size": 7,
   "trial_name": null,
   "trial_params": null