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:bb7e583f06862ae813eb17453c74d71d723f7ca33ea5ccb828d986ae99585f4a
+oid sha256:896b65f2e6ed2ede3b1813ee2b7cb468a528962aa6be2513895e9bd78f6eb2d4
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e093a45e3bb82caf69549fc82034e6093be6d5dcb4780c22db95aebfa3c22b4
+oid sha256:b235a0ba35aaefcd43e7a642341383304ac92f1b44a34cb9b392ff53086f6c9c
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c57e78ddf50e5c5295d97a992e6dd3f1e29fb23cc0494496079417867bf57901
+oid sha256:bae71cfbe25894ff1f737650c8f10781d409f7b73cf934aaad9bc03b8b169ead
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:487241e4dffeef147ec7bab3f24bb711a53c1fad16dd804f384e23301d0754e8
+oid sha256:956e8908c66f5acc581a26b38e2bec7f2cc3b327c73276c95d48f7594b7b8f7e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:600af6871e0926cb178b526c79396d0ac40e1b337076c6d7c7e03c008520222e
+oid sha256:7ee56a9c4816f3b1ac58b0ebb00af6847b092ed194a2e3f640357314c8427093
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd151d149bd072aa9e57379606edda4a60df978bb87306feffebc90fea3d8dd1
+oid sha256:0b1abbed769a1c995ae780ca12310cd93c1ae30bd52622e831f18b583abcacea
 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": 0.05177323323841574,
+  "epoch": 0.10354646647683148,
   "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": 489.586,
       "eval_steps_per_second": 127.292,
       "step": 25
+    },
+    {
+      "epoch": 0.05384416256795237,
+      "grad_norm": 0.07036886364221573,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 10.365,
+      "step": 26
+    },
+    {
+      "epoch": 0.055915091897489,
+      "grad_norm": 0.07155968248844147,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 10.3636,
+      "step": 27
+    },
+    {
+      "epoch": 0.057986021227025626,
+      "grad_norm": 0.07233037799596786,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 10.3615,
+      "step": 28
+    },
+    {
+      "epoch": 0.06005695055656226,
+      "grad_norm": 0.07332813739776611,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 10.3617,
+      "step": 29
+    },
+    {
+      "epoch": 0.062127879886098886,
+      "grad_norm": 0.08408806473016739,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 10.3586,
+      "step": 30
+    },
+    {
+      "epoch": 0.06419880921563552,
+      "grad_norm": 0.08621294796466827,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 10.3598,
+      "step": 31
+    },
+    {
+      "epoch": 0.06626973854517215,
+      "grad_norm": 0.09366805106401443,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 10.3571,
+      "step": 32
+    },
+    {
+      "epoch": 0.06834066787470877,
+      "grad_norm": 0.08554507046937943,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 10.3542,
+      "step": 33
+    },
+    {
+      "epoch": 0.0704115972042454,
+      "grad_norm": 0.0863196849822998,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 10.358,
+      "step": 34
+    },
+    {
+      "epoch": 0.07248252653378204,
+      "grad_norm": 0.07560539990663528,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 10.356,
+      "step": 35
+    },
+    {
+      "epoch": 0.07455345586331867,
+      "grad_norm": 0.07912243157625198,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 10.3522,
+      "step": 36
+    },
+    {
+      "epoch": 0.07662438519285529,
+      "grad_norm": 0.10135304182767868,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 10.3471,
+      "step": 37
+    },
+    {
+      "epoch": 0.07869531452239192,
+      "grad_norm": 0.07534138858318329,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 10.3633,
+      "step": 38
+    },
+    {
+      "epoch": 0.08076624385192856,
+      "grad_norm": 0.08607956022024155,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 10.3608,
+      "step": 39
+    },
+    {
+      "epoch": 0.08283717318146518,
+      "grad_norm": 0.08546745032072067,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 10.3591,
+      "step": 40
+    },
+    {
+      "epoch": 0.08490810251100181,
+      "grad_norm": 0.08086901903152466,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 10.3608,
+      "step": 41
+    },
+    {
+      "epoch": 0.08697903184053844,
+      "grad_norm": 0.0830010324716568,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 10.3568,
+      "step": 42
+    },
+    {
+      "epoch": 0.08904996117007508,
+      "grad_norm": 0.08770516514778137,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 10.3598,
+      "step": 43
+    },
+    {
+      "epoch": 0.0911208904996117,
+      "grad_norm": 0.09759978950023651,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 10.3554,
+      "step": 44
+    },
+    {
+      "epoch": 0.09319181982914833,
+      "grad_norm": 0.09384226053953171,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 10.3581,
+      "step": 45
+    },
+    {
+      "epoch": 0.09526274915868496,
+      "grad_norm": 0.08818507939577103,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 10.3546,
+      "step": 46
+    },
+    {
+      "epoch": 0.0973336784882216,
+      "grad_norm": 0.09831733256578445,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 10.3542,
+      "step": 47
+    },
+    {
+      "epoch": 0.09940460781775821,
+      "grad_norm": 0.09170574694871902,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 10.353,
+      "step": 48
+    },
+    {
+      "epoch": 0.10147553714729485,
+      "grad_norm": 0.09404172748327255,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 10.3514,
+      "step": 49
+    },
+    {
+      "epoch": 0.10354646647683148,
+      "grad_norm": 0.11998723447322845,
+      "learning_rate": 1e-05,
+      "loss": 10.3416,
+      "step": 50
+    },
+    {
+      "epoch": 0.10354646647683148,
+      "eval_loss": 10.350510597229004,
+      "eval_runtime": 0.1091,
+      "eval_samples_per_second": 458.113,
+      "eval_steps_per_second": 119.109,
+      "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": 21384029798400.0,
+  "total_flos": 42768059596800.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null