Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61bc31e0a1de873f2a0ac330bc0056ee1e111bec5109a9fb1ce09d9ddbd9337e
+oid sha256:8a80153b21574ec31dfb1dd856313e9b37f1623b58f6a8f2a0940ec53df1a75f
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c41da9d9e9ec38bb977699bf4a31f87721a9c8866aaa960cfc0a1dc55219b291
+oid sha256:d0241fd8d8227e1b75e80dc148eb34446de53d656327a2bc3fa3a3e85cb451ee
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5fdfd3e7f979ffaa470a267aa1bc6ba31f145354b5ac9fff40605fcf8f7dfdb
+oid sha256:fde1310990530aa4fb6d64a3fd2ee5d86e3b8e53011af2d22936c68bec3d9ab7
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6561a5fd2175f77d328627a99267638935af519d6637d34079c32d0b94de2aa
+oid sha256:68569cdf531f9a374e535a968e076c8891a64791a3020ae7e6c8d5460d2b50c3
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:835c98af81051fbb507ec37e7bd25bd9ff133a44a1b5502a5cc079be774ac2b7
+oid sha256:80810cdf94902b1e24b7d96d74ccad5dea74cc2254aeab8a9af066513d5c9bd5
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:821a4252cbbd8544ac90ed4ead1abd59f2fd91ddfb703cc9299d76f899b43349
+oid sha256:5a4b93dff6d583bad214bd98e54799ecdd2d1faf08a3d55955ac63b2aa7b81bc
 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": 0.12562814070351758,
+  "epoch": 0.25125628140703515,
   "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": 14.232,
       "eval_steps_per_second": 3.7,
       "step": 25
+    },
+    {
+      "epoch": 0.1306532663316583,
+      "grad_norm": 0.0005706869997084141,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.135678391959799,
+      "grad_norm": 0.0007929988787509501,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.1407035175879397,
+      "grad_norm": 0.04666661471128464,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.0001,
+      "step": 28
+    },
+    {
+      "epoch": 0.1457286432160804,
+      "grad_norm": 0.0005461284890770912,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.1507537688442211,
+      "grad_norm": 0.00040643519605509937,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.15577889447236182,
+      "grad_norm": 0.0005748589755967259,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.16080402010050251,
+      "grad_norm": 0.00018563361663836986,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.1658291457286432,
+      "grad_norm": 0.00019172532483935356,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.1708542713567839,
+      "grad_norm": 0.00013338103599380702,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.17587939698492464,
+      "grad_norm": 0.0001926523691508919,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.18090452261306533,
+      "grad_norm": 0.0001227665925398469,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.18592964824120603,
+      "grad_norm": 9.235703328158706e-05,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.19095477386934673,
+      "grad_norm": 0.000140156495035626,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.19597989949748743,
+      "grad_norm": 0.00012813979992643,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.20100502512562815,
+      "grad_norm": 0.0002415889030089602,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.20603015075376885,
+      "grad_norm": 0.0001376378204440698,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.21105527638190955,
+      "grad_norm": 8.98699217941612e-05,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.21608040201005024,
+      "grad_norm": 9.286760177928954e-05,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.22110552763819097,
+      "grad_norm": 0.00010751830268418416,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.22613065326633167,
+      "grad_norm": 9.245765977539122e-05,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.23115577889447236,
+      "grad_norm": 8.437052019871771e-05,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.23618090452261306,
+      "grad_norm": 5.8328838349552825e-05,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.24120603015075376,
+      "grad_norm": 6.781479896744713e-05,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.24623115577889448,
+      "grad_norm": 7.17357688699849e-05,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.25125628140703515,
+      "grad_norm": 5.727177267544903e-05,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.25125628140703515,
+      "eval_loss": 5.753825575993687e-07,
+      "eval_runtime": 3.5215,
+      "eval_samples_per_second": 14.199,
+      "eval_steps_per_second": 3.692,
+      "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": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null