Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0570314ba5a4a751d1d08ea7a6d7b442fe2ea5661d0bb4c44526d1e828a2f6ff
+oid sha256:64777874b5ca0ed488ee314c0fd767df8ed4e347eba2238026c5c91af7e4bb4e
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d20dbb38d91dbe62cc7bf7a61caea9f549ce34f54029727fdee0df9d813f9a22
+oid sha256:877c79e69a850ceee939862c2d306ae80be61a44d7b2fe7e83fdbf7950fcb9a6
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1ffbf021994a3aaf3ad3e24b59a4e454b76395a3cab013a60e6c681658e5d6b
+oid sha256:20b609ab398d8baedf96586421dceedb6244762315fb5d408a7fc6be56b14f3c
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a5506017b90fc03cbe412c551a8409022735729e66adc6df7506b139c9e0046
+oid sha256:b97fa2c522584207459fccd2858d9e2585b990f5cf90e6004d82159877d70d2d
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f0c8e1945923a444d73eed7a678eca218ae2d10fcd38662361771b323ba9e1c
+oid sha256:3760c91efe29456dbe49c6d4e3449eab8e96d37e4fdc798dfc3a81307ee01c1a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ddb96e78d3353149092f3775ae9c72a94efbe377b02ca146905eeee6d2566e8
+oid sha256:e46a6cd3311688861dc7996fcd442ca222cdc4bd56464dc9df110e5e07af155e
 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": 11.692843437194824,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.4285714285714286,
+  "best_metric": 11.67446517944336,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 2.857142857142857,
   "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": 119.864,
       "eval_steps_per_second": 31.165,
       "step": 25
+    },
+    {
+      "epoch": 1.4857142857142858,
+      "grad_norm": 0.6384664177894592,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 10.5887,
+      "step": 26
+    },
+    {
+      "epoch": 1.5428571428571427,
+      "grad_norm": 0.5847898721694946,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 12.9826,
+      "step": 27
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.5193647146224976,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 11.7588,
+      "step": 28
+    },
+    {
+      "epoch": 1.657142857142857,
+      "grad_norm": 0.6379705667495728,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 11.7865,
+      "step": 29
+    },
+    {
+      "epoch": 1.7142857142857144,
+      "grad_norm": 0.6999430656433105,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 10.8408,
+      "step": 30
+    },
+    {
+      "epoch": 1.7714285714285714,
+      "grad_norm": 0.59225994348526,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 12.1514,
+      "step": 31
+    },
+    {
+      "epoch": 1.8285714285714287,
+      "grad_norm": 0.6103184819221497,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 11.9794,
+      "step": 32
+    },
+    {
+      "epoch": 1.8857142857142857,
+      "grad_norm": 0.6637409329414368,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 12.1227,
+      "step": 33
+    },
+    {
+      "epoch": 1.9428571428571428,
+      "grad_norm": 0.6952071785926819,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 11.4498,
+      "step": 34
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.0240678787231445,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 17.2048,
+      "step": 35
+    },
+    {
+      "epoch": 2.057142857142857,
+      "grad_norm": 0.5756257772445679,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 11.6984,
+      "step": 36
+    },
+    {
+      "epoch": 2.1142857142857143,
+      "grad_norm": 0.5698725581169128,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 11.7011,
+      "step": 37
+    },
+    {
+      "epoch": 2.1714285714285713,
+      "grad_norm": 0.6899914145469666,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 11.6889,
+      "step": 38
+    },
+    {
+      "epoch": 2.2285714285714286,
+      "grad_norm": 0.7464070320129395,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 11.6845,
+      "step": 39
+    },
+    {
+      "epoch": 2.2857142857142856,
+      "grad_norm": 0.6132884621620178,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 11.6976,
+      "step": 40
+    },
+    {
+      "epoch": 2.342857142857143,
+      "grad_norm": 0.5735512375831604,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 11.6943,
+      "step": 41
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.6627440452575684,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 11.6889,
+      "step": 42
+    },
+    {
+      "epoch": 2.4571428571428573,
+      "grad_norm": 0.7545081973075867,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 11.7002,
+      "step": 43
+    },
+    {
+      "epoch": 2.5142857142857142,
+      "grad_norm": 0.6548402905464172,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 11.6905,
+      "step": 44
+    },
+    {
+      "epoch": 2.571428571428571,
+      "grad_norm": 0.607690155506134,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 11.6993,
+      "step": 45
+    },
+    {
+      "epoch": 2.6285714285714286,
+      "grad_norm": 0.6367803812026978,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 11.6844,
+      "step": 46
+    },
+    {
+      "epoch": 2.685714285714286,
+      "grad_norm": 0.7036944627761841,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 11.6783,
+      "step": 47
+    },
+    {
+      "epoch": 2.742857142857143,
+      "grad_norm": 0.6986067295074463,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 11.6745,
+      "step": 48
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.6702983975410461,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 11.6877,
+      "step": 49
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 0.6647158861160278,
+      "learning_rate": 1e-05,
+      "loss": 11.6849,
+      "step": 50
+    },
+    {
+      "epoch": 2.857142857142857,
+      "eval_loss": 11.67446517944336,
+      "eval_runtime": 0.4257,
+      "eval_samples_per_second": 117.444,
+      "eval_steps_per_second": 30.535,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 81943068672000.0,
+  "total_flos": 163886137344000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null