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:ae498ae5f6a24e3a1f442deec8cc1852a07106e461784770cfcdbb8e4cb232ee
+oid sha256:5790911e30a5f27703ed468cbcf20a0fae478f10923a56bc5f1ca881c1d16378
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba1f8c18fd2e775727225eed70ef06ff5a667ab1294d8e9616063fe85bb232a2
+oid sha256:0f9faae57db67b2cfda23fdd29bad8c31a303212c146b01550ce224657e4806c
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab0f3d7db1e86dfca038194d8f05d7f29b09c873f0a5685455ddb55c42291169
+oid sha256:c92ad178a5ee46cbf20e877ec77a957de62f03bae30288342bc636f7ed085167
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e674f61f7f69ef05853ef46575185239faee93344b1a410c09a3932cae9ea1b9
+oid sha256:d4901f39d575d31e7b63dbf1220d38031f6d1731ba59b2463bfc35386a3cf91d
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4921aeaa48659a6f8cb0dbe8fc45a53a401f3853eddc343fb3c6402135b48dc4
+oid sha256:aac7a31d1c4172dd4125985cfeb9acb7b13ecd33db0744951c0869882b251387
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c7fb71697d59dbfe3666895bd7ee71b1dbf5ec3328b0a6ad8c5918a50cb4020
+oid sha256:c3c8c11506a77041143e23e12311ad60d40c03c0fd349a4e19f675af5006c2cf
 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": 1.322988748550415,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.5988023952095808,
+  "best_metric": 1.2760416269302368,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.1991017964071857,
   "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": 15.472,
       "eval_steps_per_second": 4.023,
       "step": 25
+    },
+    {
+      "epoch": 0.6227544910179641,
+      "grad_norm": 1.3779906034469604,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.9811,
+      "step": 26
+    },
+    {
+      "epoch": 0.6467065868263473,
+      "grad_norm": 1.1780428886413574,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.6373,
+      "step": 27
+    },
+    {
+      "epoch": 0.6706586826347305,
+      "grad_norm": 1.09267258644104,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.5602,
+      "step": 28
+    },
+    {
+      "epoch": 0.6946107784431138,
+      "grad_norm": 0.8412386178970337,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.3839,
+      "step": 29
+    },
+    {
+      "epoch": 0.718562874251497,
+      "grad_norm": 1.031020998954773,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.1919,
+      "step": 30
+    },
+    {
+      "epoch": 0.7425149700598802,
+      "grad_norm": 0.7191036939620972,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.2688,
+      "step": 31
+    },
+    {
+      "epoch": 0.7664670658682635,
+      "grad_norm": 0.8087307810783386,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.2901,
+      "step": 32
+    },
+    {
+      "epoch": 0.7904191616766467,
+      "grad_norm": 0.7636876702308655,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.3111,
+      "step": 33
+    },
+    {
+      "epoch": 0.8143712574850299,
+      "grad_norm": 0.6093765497207642,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.2986,
+      "step": 34
+    },
+    {
+      "epoch": 0.8383233532934131,
+      "grad_norm": 0.6813676357269287,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.1844,
+      "step": 35
+    },
+    {
+      "epoch": 0.8622754491017964,
+      "grad_norm": 0.8225069046020508,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.7187,
+      "step": 36
+    },
+    {
+      "epoch": 0.8862275449101796,
+      "grad_norm": 0.8900802731513977,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.6647,
+      "step": 37
+    },
+    {
+      "epoch": 0.9101796407185628,
+      "grad_norm": 0.7697749733924866,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.5339,
+      "step": 38
+    },
+    {
+      "epoch": 0.9341317365269461,
+      "grad_norm": 0.6899289488792419,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.3441,
+      "step": 39
+    },
+    {
+      "epoch": 0.9580838323353293,
+      "grad_norm": 0.7491087913513184,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.2372,
+      "step": 40
+    },
+    {
+      "epoch": 0.9820359281437125,
+      "grad_norm": 1.0688893795013428,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.0752,
+      "step": 41
+    },
+    {
+      "epoch": 1.0074850299401197,
+      "grad_norm": 0.6703040599822998,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.8743,
+      "step": 42
+    },
+    {
+      "epoch": 1.031437125748503,
+      "grad_norm": 0.6135070323944092,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.1345,
+      "step": 43
+    },
+    {
+      "epoch": 1.0553892215568863,
+      "grad_norm": 0.5878804922103882,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.3387,
+      "step": 44
+    },
+    {
+      "epoch": 1.0793413173652695,
+      "grad_norm": 0.5302376747131348,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.2156,
+      "step": 45
+    },
+    {
+      "epoch": 1.1032934131736527,
+      "grad_norm": 0.6812738180160522,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.202,
+      "step": 46
+    },
+    {
+      "epoch": 1.127245508982036,
+      "grad_norm": 0.6951550245285034,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.5297,
+      "step": 47
+    },
+    {
+      "epoch": 1.151197604790419,
+      "grad_norm": 0.7668355703353882,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.5765,
+      "step": 48
+    },
+    {
+      "epoch": 1.1751497005988023,
+      "grad_norm": 0.6689496636390686,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.4226,
+      "step": 49
+    },
+    {
+      "epoch": 1.1991017964071857,
+      "grad_norm": 0.6804428696632385,
+      "learning_rate": 1e-05,
+      "loss": 1.2867,
+      "step": 50
+    },
+    {
+      "epoch": 1.1991017964071857,
+      "eval_loss": 1.2760416269302368,
+      "eval_runtime": 3.2233,
+      "eval_samples_per_second": 15.512,
+      "eval_steps_per_second": 4.033,
+      "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": 2.812028905324544e+17,
+  "total_flos": 5.624057810649088e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null