Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9eac25e841b1adefa0784fa52f328457770f09ae89703711294fc8cc8ded10cb
+oid sha256:3ad4669cee803e39fefc321c2b13b2e158dda619d12a3cf0c215a2893b5468fb
 size 116744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e33a783b3817895987b8b7e17d6344f11b9f6da10d5450f1572b55ec99c540c6
+oid sha256:101960d0fc9429e9fe679f24d3826a58652f79ce356f4e615b88ae8f824a03b6
 size 243310

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39ad929d1d20baf108120da230bb7f1383b93a7086841edb00aadeef5185c1fc
+oid sha256:5fde8b011a03169cb958bb9b13be5a66b6cab7da6427e2460f1ce3e034fab235
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e092e0c44b90287f1d7caba42c3f54a42795ffa07bdc83a6a71e5a7c17db7ebc
+oid sha256:487718e4723ddde9ca5035f2661e20f36fc4a426fd5a253742dd1d7e9aabcbaf
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e64ddd8239b569af74746105a8f12051f7e81929c43e06399e6603c24fb61eea
+oid sha256:090bf5540f16129790856c97e9efec2f3d641e8d9e030c5f7d482d53780a0027
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c3711f8de953109ca1ecc5c9f46b9aed405a459880564fc80ddaf7dd35f5ece
+oid sha256:67e6653db4c5b1990b33171ce6b9420c20ce0e04e4ccf47c1bae5ba4295fd007
 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": 0.02664890073284477,
+  "epoch": 0.05329780146568954,
   "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": 431.357,
       "eval_steps_per_second": 112.153,
       "step": 25
+    },
+    {
+      "epoch": 0.02771485676215856,
+      "grad_norm": 0.29466956853866577,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 10.3486,
+      "step": 26
+    },
+    {
+      "epoch": 0.028780812791472352,
+      "grad_norm": 0.31241559982299805,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 10.347,
+      "step": 27
+    },
+    {
+      "epoch": 0.029846768820786143,
+      "grad_norm": 0.2826091945171356,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 10.3492,
+      "step": 28
+    },
+    {
+      "epoch": 0.030912724850099934,
+      "grad_norm": 0.3171038329601288,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 10.3494,
+      "step": 29
+    },
+    {
+      "epoch": 0.031978680879413725,
+      "grad_norm": 0.304294615983963,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 10.3456,
+      "step": 30
+    },
+    {
+      "epoch": 0.03304463690872751,
+      "grad_norm": 0.3247598111629486,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 10.3515,
+      "step": 31
+    },
+    {
+      "epoch": 0.034110592938041306,
+      "grad_norm": 0.3589993119239807,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 10.346,
+      "step": 32
+    },
+    {
+      "epoch": 0.035176548967355094,
+      "grad_norm": 0.36132293939590454,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 10.3411,
+      "step": 33
+    },
+    {
+      "epoch": 0.03624250499666889,
+      "grad_norm": 0.3835195302963257,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 10.3379,
+      "step": 34
+    },
+    {
+      "epoch": 0.037308461025982675,
+      "grad_norm": 0.3723469376564026,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 10.3345,
+      "step": 35
+    },
+    {
+      "epoch": 0.03837441705529647,
+      "grad_norm": 0.3813835680484772,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 10.3435,
+      "step": 36
+    },
+    {
+      "epoch": 0.03944037308461026,
+      "grad_norm": 0.40655070543289185,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 10.3404,
+      "step": 37
+    },
+    {
+      "epoch": 0.04050632911392405,
+      "grad_norm": 0.3889438211917877,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 10.3424,
+      "step": 38
+    },
+    {
+      "epoch": 0.04157228514323784,
+      "grad_norm": 0.3690129518508911,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 10.339,
+      "step": 39
+    },
+    {
+      "epoch": 0.04263824117255163,
+      "grad_norm": 0.36811506748199463,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 10.337,
+      "step": 40
+    },
+    {
+      "epoch": 0.04370419720186542,
+      "grad_norm": 0.3503737449645996,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 10.3365,
+      "step": 41
+    },
+    {
+      "epoch": 0.044770153231179215,
+      "grad_norm": 0.3476838171482086,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 10.3357,
+      "step": 42
+    },
+    {
+      "epoch": 0.045836109260493,
+      "grad_norm": 0.40502050518989563,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 10.326,
+      "step": 43
+    },
+    {
+      "epoch": 0.046902065289806796,
+      "grad_norm": 0.37952473759651184,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 10.3307,
+      "step": 44
+    },
+    {
+      "epoch": 0.047968021319120584,
+      "grad_norm": 0.3985709846019745,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 10.3376,
+      "step": 45
+    },
+    {
+      "epoch": 0.04903397734843438,
+      "grad_norm": 0.3946983516216278,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 10.3341,
+      "step": 46
+    },
+    {
+      "epoch": 0.050099933377748165,
+      "grad_norm": 0.37759777903556824,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 10.3338,
+      "step": 47
+    },
+    {
+      "epoch": 0.05116588940706196,
+      "grad_norm": 0.40839263796806335,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 10.3287,
+      "step": 48
+    },
+    {
+      "epoch": 0.05223184543637575,
+      "grad_norm": 0.42501384019851685,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 10.3254,
+      "step": 49
+    },
+    {
+      "epoch": 0.05329780146568954,
+      "grad_norm": 0.4669570028781891,
+      "learning_rate": 1e-05,
+      "loss": 10.3262,
+      "step": 50
+    },
+    {
+      "epoch": 0.05329780146568954,
+      "eval_loss": 10.321706771850586,
+      "eval_runtime": 0.1212,
+      "eval_samples_per_second": 412.623,
+      "eval_steps_per_second": 107.282,
+      "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": 42337731870720.0,
+  "total_flos": 84675463741440.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null