Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e2fdb85d38474673a0de09cbeafed1ee81a0aca7d384c8ca7c2008f396c054c
+oid sha256:bceb4440cf3f77c0f6a061d8aeceb03d5537959e0f1a3afb84a6497fb2b33007
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:007b7ef5e3a55fc5e2baff0b9c655cf59b3f400870ebfef18a21c768d6ab4694
+oid sha256:42b12b8efc62d05622e6b3b92d6f61360d5fcbcbd71e4179a0f5d934533d2e30
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4f73f9791a79ff3e9f419fe4786ff29527d7a6e30198f901d9c8a14b407d009
+oid sha256:12872599d340595123be7860c1b5e1021b360200abdd4379f79cb711564b5117
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c08192cfa5ecc5df970c49047b1ba2404d66c2ff20a076315d4c41739b18e3fc
+oid sha256:6fe43770f6ba0f64c2ff7215cc8f661f87ae1a2053c901820dc50cae6cab83ed
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b57804e29264092f5e3b10b95dea8a525358d858aa134eed4af8e76d793f0997
+oid sha256:631300fc18b0ca6f5f6c0c36f57651ac87c1f9c2a12baff8a0aa45428375b487
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27bcb01a5e3eb3b620cd49eb7c098d2d9d3fd31e2efdf83335ce07ebd33d387b
+oid sha256:3c377db213912a02067c350b606e4c55f9f14dac5cd5a25e8123cd5edf916923
 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": 4.454497337341309,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.033803769120256906,
+  "best_metric": 4.331421375274658,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.06760753824051381,
   "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": 35.655,
       "eval_steps_per_second": 4.458,
       "step": 25
+    },
+    {
+      "epoch": 0.03515591988506719,
+      "grad_norm": 0.5346957445144653,
+      "learning_rate": 5e-05,
+      "loss": 3.7734,
+      "step": 26
+    },
+    {
+      "epoch": 0.03650807064987746,
+      "grad_norm": 0.48548877239227295,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 3.7513,
+      "step": 27
+    },
+    {
+      "epoch": 0.037860221414687735,
+      "grad_norm": 0.5325626730918884,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 3.9249,
+      "step": 28
+    },
+    {
+      "epoch": 0.039212372179498016,
+      "grad_norm": 0.559912383556366,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 3.9959,
+      "step": 29
+    },
+    {
+      "epoch": 0.04056452294430829,
+      "grad_norm": 0.5321981906890869,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 4.0154,
+      "step": 30
+    },
+    {
+      "epoch": 0.041916673709118564,
+      "grad_norm": 0.502756655216217,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 4.12,
+      "step": 31
+    },
+    {
+      "epoch": 0.043268824473928845,
+      "grad_norm": 0.4477120339870453,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 4.032,
+      "step": 32
+    },
+    {
+      "epoch": 0.04462097523873912,
+      "grad_norm": 0.4660121202468872,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 4.2817,
+      "step": 33
+    },
+    {
+      "epoch": 0.04597312600354939,
+      "grad_norm": 0.42898258566856384,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 4.3959,
+      "step": 34
+    },
+    {
+      "epoch": 0.047325276768359674,
+      "grad_norm": 0.4856753647327423,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 4.6094,
+      "step": 35
+    },
+    {
+      "epoch": 0.04867742753316995,
+      "grad_norm": 0.5574827194213867,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 4.5035,
+      "step": 36
+    },
+    {
+      "epoch": 0.05002957829798022,
+      "grad_norm": 0.9172268509864807,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 4.9945,
+      "step": 37
+    },
+    {
+      "epoch": 0.0513817290627905,
+      "grad_norm": 0.2705156207084656,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 3.5267,
+      "step": 38
+    },
+    {
+      "epoch": 0.05273387982760078,
+      "grad_norm": 0.25495946407318115,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 3.8079,
+      "step": 39
+    },
+    {
+      "epoch": 0.05408603059241105,
+      "grad_norm": 0.258202463388443,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 3.8776,
+      "step": 40
+    },
+    {
+      "epoch": 0.05543818135722133,
+      "grad_norm": 0.2978667616844177,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 3.9657,
+      "step": 41
+    },
+    {
+      "epoch": 0.056790332122031606,
+      "grad_norm": 0.3443995416164398,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 4.0358,
+      "step": 42
+    },
+    {
+      "epoch": 0.05814248288684188,
+      "grad_norm": 0.325653612613678,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 4.0879,
+      "step": 43
+    },
+    {
+      "epoch": 0.05949463365165216,
+      "grad_norm": 0.37084466218948364,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 4.1399,
+      "step": 44
+    },
+    {
+      "epoch": 0.060846784416462435,
+      "grad_norm": 0.3950638771057129,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 4.1623,
+      "step": 45
+    },
+    {
+      "epoch": 0.06219893518127271,
+      "grad_norm": 0.4259364902973175,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 4.2288,
+      "step": 46
+    },
+    {
+      "epoch": 0.06355108594608298,
+      "grad_norm": 0.5128974914550781,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 4.3181,
+      "step": 47
+    },
+    {
+      "epoch": 0.06490323671089326,
+      "grad_norm": 0.5414010882377625,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 4.408,
+      "step": 48
+    },
+    {
+      "epoch": 0.06625538747570354,
+      "grad_norm": 0.7349984049797058,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 4.7669,
+      "step": 49
+    },
+    {
+      "epoch": 0.06760753824051381,
+      "grad_norm": 1.0795515775680542,
+      "learning_rate": 0.0,
+      "loss": 5.1084,
+      "step": 50
+    },
+    {
+      "epoch": 0.06760753824051381,
+      "eval_loss": 4.331421375274658,
+      "eval_runtime": 139.8916,
+      "eval_samples_per_second": 35.62,
+      "eval_steps_per_second": 4.453,
+      "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": 2.822574037878702e+17,
+  "total_flos": 5.6433905536650445e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null