Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:189e5fe236ec13a6db3fc00c72bb1096fd3f1891a02cc8b705028cac202ef4a6
+oid sha256:3954917c1e696215a5a0ee69d222dcae3a641457c3bf178c8ab9dc39c399e025
 size 201361312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a936528f5270f898465cd7223efb69e61de541ac257cd94efba9a1c7a97ff9a1
+oid sha256:829143cebd2d65e6838bfb8c2990a6675d022210718703ceb4d260e53f015435
 size 402868986

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f773d8c1e5eea6f665d19a72f3bd53d97d4bde50e25d31229c1e007a694de0a1
+oid sha256:e7b4f3e30a6352dec64db9d61032cd9a36d40e405f06d691abec707561670786
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c59f2ca0e8e2c14be6841e65a3d7036ca4d4c26f139c31941ddd9ba05d9ce30
+oid sha256:b7c871f733d2e37c1e07e07944791a8c2322655b42da63d15f223cc4a6be5c19
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86fc35f280bcb7cb217307ef62e72319a1df5f366f2d2d13a02a8b1468b7d838
+oid sha256:5c4f96613755377c410e05ca09924094737715834b8f5531754dd7019fc68e0b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b68734057f143dcfb39e1be1a545d9690ddf30551b1703810a57f375d15a773
+oid sha256:93930bed4c9397ec7bf184f6b889c79e5caa6ac0b5ac5c706e4ddff955881e29
 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": 0.006371811107659713,
+  "epoch": 0.012743622215319427,
   "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": 10.086,
       "eval_steps_per_second": 2.622,
       "step": 25
+    },
+    {
+      "epoch": 0.006626683551966102,
+      "grad_norm": 4.532904624938965,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 18.5507,
+      "step": 26
+    },
+    {
+      "epoch": 0.006881555996272491,
+      "grad_norm": 4.218832969665527,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 21.4172,
+      "step": 27
+    },
+    {
+      "epoch": 0.007136428440578879,
+      "grad_norm": 9.199362754821777,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 22.3767,
+      "step": 28
+    },
+    {
+      "epoch": 0.0073913008848852674,
+      "grad_norm": 5.325526237487793,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 24.2828,
+      "step": 29
+    },
+    {
+      "epoch": 0.007646173329191656,
+      "grad_norm": 5.052194595336914,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 21.9941,
+      "step": 30
+    },
+    {
+      "epoch": 0.007901045773498044,
+      "grad_norm": 6.375118255615234,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 23.9578,
+      "step": 31
+    },
+    {
+      "epoch": 0.008155918217804432,
+      "grad_norm": 7.436459064483643,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 23.0201,
+      "step": 32
+    },
+    {
+      "epoch": 0.008410790662110822,
+      "grad_norm": 7.55717658996582,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 26.8142,
+      "step": 33
+    },
+    {
+      "epoch": 0.00866566310641721,
+      "grad_norm": 10.21662712097168,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 26.6104,
+      "step": 34
+    },
+    {
+      "epoch": 0.008920535550723599,
+      "grad_norm": 9.883365631103516,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 26.0736,
+      "step": 35
+    },
+    {
+      "epoch": 0.009175407995029987,
+      "grad_norm": 14.174981117248535,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 28.5612,
+      "step": 36
+    },
+    {
+      "epoch": 0.009430280439336376,
+      "grad_norm": 29.440217971801758,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 35.2239,
+      "step": 37
+    },
+    {
+      "epoch": 0.009685152883642764,
+      "grad_norm": 26.214704513549805,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 26.3995,
+      "step": 38
+    },
+    {
+      "epoch": 0.009940025327949152,
+      "grad_norm": 5.275035381317139,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 20.0292,
+      "step": 39
+    },
+    {
+      "epoch": 0.010194897772255542,
+      "grad_norm": 3.81276798248291,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 20.0261,
+      "step": 40
+    },
+    {
+      "epoch": 0.01044977021656193,
+      "grad_norm": 7.4508376121521,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 20.7993,
+      "step": 41
+    },
+    {
+      "epoch": 0.010704642660868319,
+      "grad_norm": 4.377939701080322,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 21.0901,
+      "step": 42
+    },
+    {
+      "epoch": 0.010959515105174707,
+      "grad_norm": 5.861658573150635,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 21.6036,
+      "step": 43
+    },
+    {
+      "epoch": 0.011214387549481095,
+      "grad_norm": 4.197175025939941,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 22.2189,
+      "step": 44
+    },
+    {
+      "epoch": 0.011469259993787484,
+      "grad_norm": 4.8456010818481445,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 23.1757,
+      "step": 45
+    },
+    {
+      "epoch": 0.011724132438093872,
+      "grad_norm": 21.775585174560547,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 24.6419,
+      "step": 46
+    },
+    {
+      "epoch": 0.011979004882400262,
+      "grad_norm": 11.26821231842041,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 25.9023,
+      "step": 47
+    },
+    {
+      "epoch": 0.01223387732670665,
+      "grad_norm": 10.412407875061035,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 27.6609,
+      "step": 48
+    },
+    {
+      "epoch": 0.012488749771013039,
+      "grad_norm": 13.727615356445312,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 26.2059,
+      "step": 49
+    },
+    {
+      "epoch": 0.012743622215319427,
+      "grad_norm": 21.477025985717773,
+      "learning_rate": 1e-05,
+      "loss": 34.0621,
+      "step": 50
+    },
+    {
+      "epoch": 0.012743622215319427,
+      "eval_loss": 0.8061414957046509,
+      "eval_runtime": 4.9334,
+      "eval_samples_per_second": 10.135,
+      "eval_steps_per_second": 2.635,
+      "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": 1.505822341500764e+17,
+  "total_flos": 3.0139627627505254e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null