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:b3d3784ee66dadac9792d6555da6baf0bc64b886e399873ed5e6a6ae955db709
+oid sha256:6e7b8c0c2c2d076766cccb43bba296f03a1f10fb983f03fc415d34ea9e2364af
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:262c610352d3de9edf30817a7e15e0a39ad1f219fe895a18b935d0a1f047bdcc
+oid sha256:0de2f8301eb4cb62e446901e3071cfdfd4b5fb4f5b66bf9fe283bbe15b6d1bf5
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:054158269091d2237f6071e58d1c72bb4f599aaecc5ff11f2eca77d94c2c2632
+oid sha256:9af115532c93685200c401eaa07fa6b63a6438513550a02eb834c41acd39e66c
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10de6fedde498d5007724f6c510065f7eb6619316da90df391d62634b536f5df
+oid sha256:8a3627421b45bf01b97f04359f27795f8d8b9b38fc6c6a7d581e1b3d94044a0e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:839746f9984ccbbbd9bbfe9843616a5d41ddb4c5512d8fccfe96db6c85a206a4
+oid sha256:bed86cf6d09180aa3014103c7e367b0228f7ee8349e89ab3b34c8a9cf51882a3
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60b2fdf8a16257a4e6ecd063178fe2d3b70186add8daf4d12857cbf9f5c47b80
+oid sha256:2a7c379d56dbc8337c2cb93782eb5c085bac6900a0aeef98ab199513dce94c47
 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": 0.062315002336812586,
+  "epoch": 0.12463000467362517,
   "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": 13.942,
       "eval_steps_per_second": 3.625,
       "step": 25
+    },
+    {
+      "epoch": 0.06480760243028509,
+      "grad_norm": 12.182744979858398,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 39.6703,
+      "step": 26
+    },
+    {
+      "epoch": 0.0673002025237576,
+      "grad_norm": 9.66840934753418,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 41.0538,
+      "step": 27
+    },
+    {
+      "epoch": 0.0697928026172301,
+      "grad_norm": 7.723933219909668,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 40.8829,
+      "step": 28
+    },
+    {
+      "epoch": 0.0722854027107026,
+      "grad_norm": 10.423388481140137,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 41.5667,
+      "step": 29
+    },
+    {
+      "epoch": 0.07477800280417511,
+      "grad_norm": 11.415440559387207,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 42.001,
+      "step": 30
+    },
+    {
+      "epoch": 0.0772706028976476,
+      "grad_norm": 9.448587417602539,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 44.3011,
+      "step": 31
+    },
+    {
+      "epoch": 0.07976320299112011,
+      "grad_norm": 8.649128913879395,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 42.1353,
+      "step": 32
+    },
+    {
+      "epoch": 0.08225580308459261,
+      "grad_norm": 9.245633125305176,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 42.307,
+      "step": 33
+    },
+    {
+      "epoch": 0.08474840317806512,
+      "grad_norm": 10.58106517791748,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 44.1531,
+      "step": 34
+    },
+    {
+      "epoch": 0.08724100327153762,
+      "grad_norm": 12.213338851928711,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 44.9653,
+      "step": 35
+    },
+    {
+      "epoch": 0.08973360336501013,
+      "grad_norm": 18.405900955200195,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 48.0947,
+      "step": 36
+    },
+    {
+      "epoch": 0.09222620345848263,
+      "grad_norm": 22.227853775024414,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 50.5871,
+      "step": 37
+    },
+    {
+      "epoch": 0.09471880355195514,
+      "grad_norm": 31.471637725830078,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 50.5865,
+      "step": 38
+    },
+    {
+      "epoch": 0.09721140364542763,
+      "grad_norm": 8.112051010131836,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 37.6254,
+      "step": 39
+    },
+    {
+      "epoch": 0.09970400373890013,
+      "grad_norm": 7.1719441413879395,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 38.5991,
+      "step": 40
+    },
+    {
+      "epoch": 0.10219660383237264,
+      "grad_norm": 6.442931175231934,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 39.739,
+      "step": 41
+    },
+    {
+      "epoch": 0.10468920392584515,
+      "grad_norm": 5.925367832183838,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 40.6377,
+      "step": 42
+    },
+    {
+      "epoch": 0.10718180401931765,
+      "grad_norm": 6.379517555236816,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 41.3528,
+      "step": 43
+    },
+    {
+      "epoch": 0.10967440411279016,
+      "grad_norm": 8.130070686340332,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 41.3185,
+      "step": 44
+    },
+    {
+      "epoch": 0.11216700420626266,
+      "grad_norm": 8.644542694091797,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 43.0408,
+      "step": 45
+    },
+    {
+      "epoch": 0.11465960429973517,
+      "grad_norm": 10.712021827697754,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 41.6555,
+      "step": 46
+    },
+    {
+      "epoch": 0.11715220439320767,
+      "grad_norm": 11.649221420288086,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 43.8152,
+      "step": 47
+    },
+    {
+      "epoch": 0.11964480448668016,
+      "grad_norm": 14.572856903076172,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 45.252,
+      "step": 48
+    },
+    {
+      "epoch": 0.12213740458015267,
+      "grad_norm": 19.085554122924805,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 47.54,
+      "step": 49
+    },
+    {
+      "epoch": 0.12463000467362517,
+      "grad_norm": 31.62267303466797,
+      "learning_rate": 1e-05,
+      "loss": 54.4587,
+      "step": 50
+    },
+    {
+      "epoch": 0.12463000467362517,
+      "eval_loss": 1.5832980871200562,
+      "eval_runtime": 3.8011,
+      "eval_samples_per_second": 13.154,
+      "eval_steps_per_second": 3.42,
+      "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": 2.7840385819816755e+17,
+  "total_flos": 5.573829327763538e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null