Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00b3fd3e5ed1dddbac004916a1fb3d661a4c08fbe8043ac3119b3f55e8e82310
+oid sha256:ae32f4fd1d9559e66dba12b44e711546da2223b02c4ef5cd9963337521964764
 size 239536272

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18c34b2bc2478355873b693344883ee783d62e33b3ef4af8573faec6c762908e
+oid sha256:a28507894658ddea376a45c516765ef740b9a7e6647cb16c68626f89a1e9e801
 size 479362682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:256420be6458892cdef978bd65e1780b4c8cc18f77bfe0d2a26342bff9c22bdd
+oid sha256:29d1678e1708f3ee9a60b3103b9c07330fc14f63e26f006b67c54f950342a6ee
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6579e6299835836f0f46aafa993e6ff7230ffca337fc3ddbac5805716a195900
+oid sha256:230e310eb0f8128a6f8daecbd7b0b2530804d7f70fcd742cae54bc8e8cbe618c
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec4dbde82a34dbe2cfa53a8bde9bc2f2927cedaef0c6c9f99ec22649bd51288c
+oid sha256:fd18ea5d9d3f6b97d0f26d444381f601c5ce9000f43af57c242595a4eed0331c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d5b2f335fe522e78bef3175802059c1578e9b9990a96375a01dc330da926e05
+oid sha256:6df9dc7059fff2228ffe7e4dc77373b3f131c152e896f0c2be96354f99a5ae9f
 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": 0.04463077709078789,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0378823752249266,
+  "best_metric": 0.019390935078263283,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.0757647504498532,
   "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": 24.57,
       "eval_steps_per_second": 3.073,
       "step": 25
+    },
+    {
+      "epoch": 0.03939767023392367,
+      "grad_norm": 0.9107250571250916,
+      "learning_rate": 5e-05,
+      "loss": 0.1028,
+      "step": 26
+    },
+    {
+      "epoch": 0.04091296524292073,
+      "grad_norm": 0.7101989388465881,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.0304,
+      "step": 27
+    },
+    {
+      "epoch": 0.042428260251917795,
+      "grad_norm": 1.0392823219299316,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0344,
+      "step": 28
+    },
+    {
+      "epoch": 0.04394355526091486,
+      "grad_norm": 0.15780067443847656,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.0036,
+      "step": 29
+    },
+    {
+      "epoch": 0.04545885026991192,
+      "grad_norm": 0.21417230367660522,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0131,
+      "step": 30
+    },
+    {
+      "epoch": 0.04697414527890899,
+      "grad_norm": 0.0216988455504179,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.0003,
+      "step": 31
+    },
+    {
+      "epoch": 0.048489440287906055,
+      "grad_norm": 0.4536718726158142,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0291,
+      "step": 32
+    },
+    {
+      "epoch": 0.050004735296903115,
+      "grad_norm": 0.3569079339504242,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.0092,
+      "step": 33
+    },
+    {
+      "epoch": 0.05152003030590018,
+      "grad_norm": 0.48347148299217224,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0411,
+      "step": 34
+    },
+    {
+      "epoch": 0.05303532531489724,
+      "grad_norm": 0.6319137811660767,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.0184,
+      "step": 35
+    },
+    {
+      "epoch": 0.05455062032389431,
+      "grad_norm": 0.7386607527732849,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.0159,
+      "step": 36
+    },
+    {
+      "epoch": 0.056065915332891375,
+      "grad_norm": 0.5089266300201416,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.021,
+      "step": 37
+    },
+    {
+      "epoch": 0.057581210341888435,
+      "grad_norm": 0.7640270590782166,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.04,
+      "step": 38
+    },
+    {
+      "epoch": 0.0590965053508855,
+      "grad_norm": 0.6873552799224854,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.1023,
+      "step": 39
+    },
+    {
+      "epoch": 0.06061180035988256,
+      "grad_norm": 0.12157164514064789,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0019,
+      "step": 40
+    },
+    {
+      "epoch": 0.06212709536887963,
+      "grad_norm": 0.738184928894043,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.0168,
+      "step": 41
+    },
+    {
+      "epoch": 0.0636423903778767,
+      "grad_norm": 0.1921297013759613,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0172,
+      "step": 42
+    },
+    {
+      "epoch": 0.06515768538687376,
+      "grad_norm": 0.37481895089149475,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.0128,
+      "step": 43
+    },
+    {
+      "epoch": 0.06667298039587082,
+      "grad_norm": 0.006890297867357731,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0001,
+      "step": 44
+    },
+    {
+      "epoch": 0.06818827540486788,
+      "grad_norm": 0.07707437872886658,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.0016,
+      "step": 45
+    },
+    {
+      "epoch": 0.06970357041386495,
+      "grad_norm": 0.3020615875720978,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0127,
+      "step": 46
+    },
+    {
+      "epoch": 0.07121886542286202,
+      "grad_norm": 0.006439794786274433,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.0001,
+      "step": 47
+    },
+    {
+      "epoch": 0.07273416043185908,
+      "grad_norm": 0.3382377624511719,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0101,
+      "step": 48
+    },
+    {
+      "epoch": 0.07424945544085614,
+      "grad_norm": 0.3824474811553955,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.0181,
+      "step": 49
+    },
+    {
+      "epoch": 0.0757647504498532,
+      "grad_norm": 0.9669052362442017,
+      "learning_rate": 0.0,
+      "loss": 0.0722,
+      "step": 50
+    },
+    {
+      "epoch": 0.0757647504498532,
+      "eval_loss": 0.019390935078263283,
+      "eval_runtime": 180.982,
+      "eval_samples_per_second": 24.566,
+      "eval_steps_per_second": 3.072,
+      "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": 1.1153227982569472e+17,
+  "total_flos": 2.2299489528184832e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null