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:e531139170542d84959b21cbf3a26791afa47dc789f3c7965fdbf30a5c0c9e94
+oid sha256:372925dbcf72188c0a3c15366987fb19796cd7362145f4da30a020df66ee558b
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98f8e339ea8f3e0e54ccd7582bc87e2bc32f3fff15ae0f8efdb666927cbdec43
+oid sha256:172aba0cd93ebc43d7652192978a5185e25c147482400dd21b0bc62862668064
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d0a622a4cd60b6f562e679e24985ad6b5eab88ebc342aac7e834009df7ea63a
+oid sha256:bb1afbd0bef91c870f350f5770233d2da078399f33518c0f95063c652b15bf2b
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c18603b79d16086b7e51cac4f5dfca8fcd3b97468545c71a2beb96ec0abe199
+oid sha256:73de654b98adb11b458a25d441755c165ad967ff0772ef9bbcfa7a3a436f9c9d
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55bec0564044ec66e77acc64ed4a02cd459135dc71bdfec0aa17c040e21120e3
+oid sha256:0c102bd6640c7d43841824c433918a7ceaa41c6a2698bdd388fb6da33e3e6e97
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3991e1dc2e0fd7058f351be5a4a2d401ffe99efcbd5e250ed0e162cbf14b88fa
+oid sha256:2e3ccb3d86b9014d9a49ac8349ef4c988569635aa592945105801f0787ed92cf
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01273013700809955,
+  "epoch": 0.0254602740161991,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 15.478,
       "eval_steps_per_second": 4.024,
       "step": 25
+    },
+    {
+      "epoch": 0.013239342488423532,
+      "grad_norm": 0.2677386403083801,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.4179,
+      "step": 26
+    },
+    {
+      "epoch": 0.013748547968747514,
+      "grad_norm": 0.33854132890701294,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.152,
+      "step": 27
+    },
+    {
+      "epoch": 0.014257753449071495,
+      "grad_norm": 0.42675265669822693,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.8932,
+      "step": 28
+    },
+    {
+      "epoch": 0.014766958929395477,
+      "grad_norm": 0.26116687059402466,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.3545,
+      "step": 29
+    },
+    {
+      "epoch": 0.01527616440971946,
+      "grad_norm": 0.24653884768486023,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.2111,
+      "step": 30
+    },
+    {
+      "epoch": 0.015785369890043442,
+      "grad_norm": 0.2200997769832611,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.2262,
+      "step": 31
+    },
+    {
+      "epoch": 0.016294575370367423,
+      "grad_norm": 0.23955288529396057,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.313,
+      "step": 32
+    },
+    {
+      "epoch": 0.016803780850691407,
+      "grad_norm": 0.24517883360385895,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.3234,
+      "step": 33
+    },
+    {
+      "epoch": 0.017312986331015388,
+      "grad_norm": 0.2714325487613678,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.2972,
+      "step": 34
+    },
+    {
+      "epoch": 0.01782219181133937,
+      "grad_norm": 0.30093419551849365,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.2841,
+      "step": 35
+    },
+    {
+      "epoch": 0.018331397291663352,
+      "grad_norm": 0.33117982745170593,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.2362,
+      "step": 36
+    },
+    {
+      "epoch": 0.018840602771987333,
+      "grad_norm": 0.4416939914226532,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.2139,
+      "step": 37
+    },
+    {
+      "epoch": 0.019349808252311314,
+      "grad_norm": 0.34697452187538147,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.3128,
+      "step": 38
+    },
+    {
+      "epoch": 0.019859013732635298,
+      "grad_norm": 0.2264784425497055,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.3141,
+      "step": 39
+    },
+    {
+      "epoch": 0.02036821921295928,
+      "grad_norm": 0.2044232338666916,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.1041,
+      "step": 40
+    },
+    {
+      "epoch": 0.020877424693283263,
+      "grad_norm": 0.19597738981246948,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.2327,
+      "step": 41
+    },
+    {
+      "epoch": 0.021386630173607243,
+      "grad_norm": 0.21620656549930573,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.3149,
+      "step": 42
+    },
+    {
+      "epoch": 0.021895835653931224,
+      "grad_norm": 0.1993994116783142,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.112,
+      "step": 43
+    },
+    {
+      "epoch": 0.022405041134255208,
+      "grad_norm": 0.21210165321826935,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.3416,
+      "step": 44
+    },
+    {
+      "epoch": 0.02291424661457919,
+      "grad_norm": 0.23273739218711853,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.3287,
+      "step": 45
+    },
+    {
+      "epoch": 0.023423452094903173,
+      "grad_norm": 0.23162347078323364,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.3328,
+      "step": 46
+    },
+    {
+      "epoch": 0.023932657575227154,
+      "grad_norm": 0.27658507227897644,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.2636,
+      "step": 47
+    },
+    {
+      "epoch": 0.024441863055551134,
+      "grad_norm": 0.2997262477874756,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.2213,
+      "step": 48
+    },
+    {
+      "epoch": 0.02495106853587512,
+      "grad_norm": 0.3726732134819031,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.2438,
+      "step": 49
+    },
+    {
+      "epoch": 0.0254602740161991,
+      "grad_norm": 0.5719786286354065,
+      "learning_rate": 1e-05,
+      "loss": 1.0469,
+      "step": 50
+    },
+    {
+      "epoch": 0.0254602740161991,
+      "eval_loss": 1.1436867713928223,
+      "eval_runtime": 3.258,
+      "eval_samples_per_second": 15.347,
+      "eval_steps_per_second": 3.99,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -212,12 +395,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.812028905324544e+17,
+  "total_flos": 5.624057810649088e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null