Training in progress, step 20, checkpoint

last-checkpoint/model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85b17fb7f911aac944c07f7d1e60d4aff773114a73adcd1c432996250386e07e
+oid sha256:6f3d812570002e67e4c524bc9167715869351666b679db2c2113d31ed4a9130f
 size 4972163696

last-checkpoint/model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52ffa09e7423c38be4314cbbc1311ec46c75e31ecc5a2d4f0df329edce91a7de
+oid sha256:71f5715344e5f551de03351627f6738c6b66ba1ac393a2f90e551e5e4e2de1cf
 size 2669366920

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3370ea74be7a6019e3b178abb23d9154cad8f6ede71322ae3b44f18537ff33c8
+oid sha256:c6d8e5d7ab5b6813cfdaaee212fdefc8fafe46fd7ea65d8db8ccc0bcbea79b75
 size 7762295162

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02b8d06323d7782eba280757f4398dbd280b072f40187b91d87fe4f49d7e6828
-size 14512
+oid sha256:1f60241cb6cb86cf9966e8cfe2248be00bce643b5808e2c3b78c9cb618eea253
+size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fe37d9f1cbca235c339a9316b5b88784b3b45f0c10ef4f8070517c1de6878f5
-size 14512
+oid sha256:2e76feebe960d60536ad1ed0bcaee2e12a3f8432f33b7ee3b0cae559b12130c0
+size 15024

last-checkpoint/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f5988c600823ef881ed3900c9909420e69870efab70abf3dca0673a3c88b057
+size 15024

last-checkpoint/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7090a3c6759641db81e3ee589636615551bb1b7ce0948f2fd4ab7d7beb35de9c
+size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f07ce69a2abeb161a8250a6ab5003f92f86de92b90dabd232da31b8c613fe6b7
+oid sha256:e3d7496cd5cad5fcd343f51f06f864ca525a833da3ba71e9c4d90915510423ac
 size 1064

last-checkpoint/trainer_state.json

@@ -1,199 +1,49 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.8867924528301887,
-  "eval_steps": 50,
-  "global_step": 200,
+  "epoch": 0.37735849056603776,
+  "eval_steps": 20,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.009433962264150943,
-      "eval_loss": 1.9632965326309204,
-      "eval_runtime": 38.8614,
-      "eval_samples_per_second": 38.624,
-      "eval_steps_per_second": 4.838,
+      "epoch": 0.018867924528301886,
+      "eval_loss": 1.9572468996047974,
+      "eval_runtime": 19.4145,
+      "eval_samples_per_second": 77.313,
+      "eval_steps_per_second": 4.842,
       "step": 1
     },
     {
-      "epoch": 0.09433962264150944,
-      "grad_norm": 1.8203125,
-      "learning_rate": 3.0769230769230774e-05,
-      "loss": 1.7057,
+      "epoch": 0.18867924528301888,
+      "grad_norm": 1.59375,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 1.6912,
       "step": 10
     },
     {
-      "epoch": 0.18867924528301888,
-      "grad_norm": 1.3515625,
-      "learning_rate": 6.153846153846155e-05,
-      "loss": 1.6334,
+      "epoch": 0.37735849056603776,
+      "grad_norm": 1.1015625,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 1.6237,
       "step": 20
     },
-    {
-      "epoch": 0.2830188679245283,
-      "grad_norm": 1.84375,
-      "learning_rate": 9.230769230769232e-05,
-      "loss": 1.5965,
-      "step": 30
-    },
     {
       "epoch": 0.37735849056603776,
-      "grad_norm": 1.34375,
-      "learning_rate": 0.0001230769230769231,
-      "loss": 1.6454,
-      "step": 40
-    },
-    {
-      "epoch": 0.4716981132075472,
-      "grad_norm": 1.375,
-      "learning_rate": 0.00015384615384615385,
-      "loss": 1.8336,
-      "step": 50
-    },
-    {
-      "epoch": 0.4716981132075472,
-      "eval_loss": 1.5319143533706665,
-      "eval_runtime": 37.268,
-      "eval_samples_per_second": 40.276,
-      "eval_steps_per_second": 5.045,
-      "step": 50
-    },
-    {
-      "epoch": 0.5660377358490566,
-      "grad_norm": 1.390625,
-      "learning_rate": 0.00018461538461538463,
-      "loss": 1.6412,
-      "step": 60
-    },
-    {
-      "epoch": 0.660377358490566,
-      "grad_norm": 1.1796875,
-      "learning_rate": 0.0001999919114627769,
-      "loss": 1.6797,
-      "step": 70
-    },
-    {
-      "epoch": 0.7547169811320755,
-      "grad_norm": 0.94140625,
-      "learning_rate": 0.00019992721101571236,
-      "loss": 1.7777,
-      "step": 80
-    },
-    {
-      "epoch": 0.8490566037735849,
-      "grad_norm": 1.1640625,
-      "learning_rate": 0.00019979785198644806,
-      "loss": 1.7622,
-      "step": 90
-    },
-    {
-      "epoch": 0.9433962264150944,
-      "grad_norm": 1.5078125,
-      "learning_rate": 0.00019960391807762463,
-      "loss": 1.7494,
-      "step": 100
-    },
-    {
-      "epoch": 0.9433962264150944,
-      "eval_loss": 1.6423826217651367,
-      "eval_runtime": 38.0472,
-      "eval_samples_per_second": 39.451,
-      "eval_steps_per_second": 4.941,
-      "step": 100
-    },
-    {
-      "epoch": 1.0377358490566038,
-      "grad_norm": 1.6875,
-      "learning_rate": 0.00019934553477549794,
-      "loss": 1.5189,
-      "step": 110
-    },
-    {
-      "epoch": 1.1320754716981132,
-      "grad_norm": 1.21875,
-      "learning_rate": 0.0001990228692687429,
-      "loss": 1.117,
-      "step": 120
-    },
-    {
-      "epoch": 1.2264150943396226,
-      "grad_norm": 1.03125,
-      "learning_rate": 0.00019863613034027224,
-      "loss": 1.3558,
-      "step": 130
-    },
-    {
-      "epoch": 1.320754716981132,
-      "grad_norm": 1.1484375,
-      "learning_rate": 0.00019818556823214268,
-      "loss": 1.1093,
-      "step": 140
-    },
-    {
-      "epoch": 1.4150943396226414,
-      "grad_norm": 1.109375,
-      "learning_rate": 0.00019767147448363366,
-      "loss": 1.0954,
-      "step": 150
-    },
-    {
-      "epoch": 1.4150943396226414,
-      "eval_loss": 1.7661364078521729,
-      "eval_runtime": 37.4546,
-      "eval_samples_per_second": 40.075,
-      "eval_steps_per_second": 5.019,
-      "step": 150
-    },
-    {
-      "epoch": 1.509433962264151,
-      "grad_norm": 1.109375,
-      "learning_rate": 0.0001970941817426052,
-      "loss": 1.1547,
-      "step": 160
-    },
-    {
-      "epoch": 1.6037735849056602,
-      "grad_norm": 1.0625,
-      "learning_rate": 0.00019645406355025565,
-      "loss": 1.1128,
-      "step": 170
-    },
-    {
-      "epoch": 1.6981132075471699,
-      "grad_norm": 1.359375,
-      "learning_rate": 0.0001957515340994193,
-      "loss": 1.1186,
-      "step": 180
-    },
-    {
-      "epoch": 1.7924528301886793,
-      "grad_norm": 1.15625,
-      "learning_rate": 0.00019498704796656018,
-      "loss": 1.1258,
-      "step": 190
-    },
-    {
-      "epoch": 1.8867924528301887,
-      "grad_norm": 1.046875,
-      "learning_rate": 0.00019416109981763526,
-      "loss": 1.3996,
-      "step": 200
-    },
-    {
-      "epoch": 1.8867924528301887,
-      "eval_loss": 1.7602568864822388,
-      "eval_runtime": 36.8589,
-      "eval_samples_per_second": 40.723,
-      "eval_steps_per_second": 5.101,
-      "step": 200
+      "eval_loss": 1.5020643472671509,
+      "eval_runtime": 18.3981,
+      "eval_samples_per_second": 81.584,
+      "eval_steps_per_second": 5.109,
+      "step": 20
     }
   ],
   "logging_steps": 10,
-  "max_steps": 1300,
+  "max_steps": 600,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 13,
-  "save_steps": 50,
+  "num_train_epochs": 12,
+  "save_steps": 20,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -206,7 +56,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.313993787611546e+16,
+  "total_flos": 1.463713580187648e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:899fb22d8728c672dc9aaedc431359fdbdbfbd5b7a9873d1f61a5375b7b7faef
+oid sha256:b6fc8e85610e9c1d7355072f44fd8ceaef90645fb06533af173045356dc826ea
 size 7032