Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:417fe133ea1bf4aa729c6aa197fd3d296b7b2add46884bd80b8c1d71b98bb0b4
+oid sha256:8c3e3844e7f6565f280906159086c4a0d047d8ac1edef4156ab064d72f9f52fe
 size 90207248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:988d84bda39e132abbde0e28ec0c937c87c41835f1bfc10efce108fd07ef8bbb
+oid sha256:86369878a40527dabf64361326410fbd38e5384bdea0665f9700d5ce3320a331
 size 180543866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:964759fca645e01c087f3d8c544c86a13067632d72f4974adef7869c7e4356a8
+oid sha256:cb02132f7a658648b8f553ebb970c1f7f992674752e0717260dcfd6d58217fa1
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0421e6435505db40f7ca76af560062f2f7496e1d62184bc958e0a6bc6c0fb32c
+oid sha256:b60d6067ded0a019ef610b4404642f9297a18a22b14d5a9f8f2a711bbb90be91
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:533372a0ae61a15d34ae067e66903af733962fcbd48240af0d6de3c044e9671c
+oid sha256:47260bc089d72b8dde4f40c91ae5e4cc9ff8eec623a798a78f7d0f89b269f29c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d684797e1a0329d7c1bcb37dc74dd456c154b95cc1504d1633bc203b3ef3919
+oid sha256:b11cc363658bff99cd697f48de82b091917d59c9d82814357b007a59fa9b0676
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 3.04049015045166,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.3249390739236393,
+  "best_metric": 2.906017303466797,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.6498781478472786,
   "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": 115.032,
       "eval_steps_per_second": 14.407,
       "step": 25
+    },
+    {
+      "epoch": 0.3379366368805849,
+      "grad_norm": 1.285607933998108,
+      "learning_rate": 5e-05,
+      "loss": 3.074,
+      "step": 26
+    },
+    {
+      "epoch": 0.35093419983753044,
+      "grad_norm": 1.0849254131317139,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 3.0416,
+      "step": 27
+    },
+    {
+      "epoch": 0.36393176279447603,
+      "grad_norm": 0.8848364353179932,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 3.0016,
+      "step": 28
+    },
+    {
+      "epoch": 0.37692932575142163,
+      "grad_norm": 0.8195856213569641,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 2.9401,
+      "step": 29
+    },
+    {
+      "epoch": 0.38992688870836717,
+      "grad_norm": 0.7989217042922974,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 2.9424,
+      "step": 30
+    },
+    {
+      "epoch": 0.40292445166531277,
+      "grad_norm": 1.0459684133529663,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 3.0352,
+      "step": 31
+    },
+    {
+      "epoch": 0.4159220146222583,
+      "grad_norm": 0.9750694036483765,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 2.9754,
+      "step": 32
+    },
+    {
+      "epoch": 0.4289195775792039,
+      "grad_norm": 0.9632560014724731,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 2.9216,
+      "step": 33
+    },
+    {
+      "epoch": 0.44191714053614944,
+      "grad_norm": 0.8961259722709656,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.9141,
+      "step": 34
+    },
+    {
+      "epoch": 0.45491470349309504,
+      "grad_norm": 0.8920239210128784,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 2.9091,
+      "step": 35
+    },
+    {
+      "epoch": 0.46791226645004064,
+      "grad_norm": 0.9372305870056152,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 2.9598,
+      "step": 36
+    },
+    {
+      "epoch": 0.4809098294069862,
+      "grad_norm": 0.9390608072280884,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 2.8996,
+      "step": 37
+    },
+    {
+      "epoch": 0.4939073923639318,
+      "grad_norm": 0.8650014996528625,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.9825,
+      "step": 38
+    },
+    {
+      "epoch": 0.5069049553208773,
+      "grad_norm": 1.0225095748901367,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 3.0036,
+      "step": 39
+    },
+    {
+      "epoch": 0.5199025182778229,
+      "grad_norm": 0.9922052621841431,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 2.9469,
+      "step": 40
+    },
+    {
+      "epoch": 0.5329000812347685,
+      "grad_norm": 0.9688642621040344,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 2.9164,
+      "step": 41
+    },
+    {
+      "epoch": 0.545897644191714,
+      "grad_norm": 0.8949860334396362,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.9194,
+      "step": 42
+    },
+    {
+      "epoch": 0.5588952071486596,
+      "grad_norm": 0.768169641494751,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 2.9348,
+      "step": 43
+    },
+    {
+      "epoch": 0.5718927701056052,
+      "grad_norm": 0.8468419313430786,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.9256,
+      "step": 44
+    },
+    {
+      "epoch": 0.5848903330625508,
+      "grad_norm": 0.7886675000190735,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 2.8906,
+      "step": 45
+    },
+    {
+      "epoch": 0.5978878960194963,
+      "grad_norm": 0.8044082522392273,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 2.8235,
+      "step": 46
+    },
+    {
+      "epoch": 0.6108854589764419,
+      "grad_norm": 0.7295715808868408,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 2.8605,
+      "step": 47
+    },
+    {
+      "epoch": 0.6238830219333875,
+      "grad_norm": 0.7860828638076782,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 2.9205,
+      "step": 48
+    },
+    {
+      "epoch": 0.6368805848903331,
+      "grad_norm": 0.7991708517074585,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 2.8495,
+      "step": 49
+    },
+    {
+      "epoch": 0.6498781478472786,
+      "grad_norm": 0.9875921607017517,
+      "learning_rate": 0.0,
+      "loss": 2.891,
+      "step": 50
+    },
+    {
+      "epoch": 0.6498781478472786,
+      "eval_loss": 2.906017303466797,
+      "eval_runtime": 4.5116,
+      "eval_samples_per_second": 115.037,
+      "eval_steps_per_second": 14.407,
+      "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": 3.91521434075136e+16,
+  "total_flos": 7.83042868150272e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null