Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4182d067cd29d7018d450cb905e15658a13ee8faea9e54f462a089035867111e
+oid sha256:29c4141ca9de99b835385674b9e711d4994fa9ee1518c1aadd21f633a32eef04
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a83c74ddef4554f8e96bc6a15f8088274eaabfa0799b2560a066eb75c2dc366
+oid sha256:cf874069f924e6e496047172ca2378bda46365b2974ca0f0ed540ba83c18f175
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e4c499328b8597983e1911618fb8ded020f5d586514ed33012c0e6176094785
+oid sha256:b497c5b68816343c798a766916cd83143804bbf1a0ba20f304247be677453e01
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1467759fe7983e8fbecce735663209eb0d1dd7fc216aba828ffeb86aa89c1058
+oid sha256:4f01b21f8a87f28f7ad5330fefdb6bd0ba3f0a89d0bca02711b2615663485e7f
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd639acc7b0441ed7d165c841172f48fd5385c83a2dda5ab5279eb8af90ecff9
+oid sha256:2721100065ebd9e1f3323d17620c882f37e7e4940c9e0787c5ee76d7f98f5f02
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e5c917e06b503e9e7ccd99a7ccda7b810de568bb04fd17d9adc129d488b6498
+oid sha256:621abdff7d2ce1ea756c8b181a74fbd82af5ce5a7cba8c124f413dcc3fcbec43
 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": 0.3096383512020111,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.6861063464837049,
+  "best_metric": 0.23947130143642426,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.3722126929674099,
   "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": 32.898,
       "eval_steps_per_second": 4.146,
       "step": 25
+    },
+    {
+      "epoch": 0.7135506003430532,
+      "grad_norm": 1.412707805633545,
+      "learning_rate": 5e-05,
+      "loss": 0.2791,
+      "step": 26
+    },
+    {
+      "epoch": 0.7409948542024014,
+      "grad_norm": 3.2293643951416016,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.3073,
+      "step": 27
+    },
+    {
+      "epoch": 0.7684391080617495,
+      "grad_norm": 2.6210861206054688,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.2711,
+      "step": 28
+    },
+    {
+      "epoch": 0.7958833619210978,
+      "grad_norm": 1.1996179819107056,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.284,
+      "step": 29
+    },
+    {
+      "epoch": 0.823327615780446,
+      "grad_norm": 1.061237096786499,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.2495,
+      "step": 30
+    },
+    {
+      "epoch": 0.8507718696397941,
+      "grad_norm": 3.171156644821167,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.2924,
+      "step": 31
+    },
+    {
+      "epoch": 0.8782161234991424,
+      "grad_norm": 3.558387279510498,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.2806,
+      "step": 32
+    },
+    {
+      "epoch": 0.9056603773584906,
+      "grad_norm": 2.23264217376709,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.2428,
+      "step": 33
+    },
+    {
+      "epoch": 0.9331046312178388,
+      "grad_norm": 0.7858607172966003,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.2808,
+      "step": 34
+    },
+    {
+      "epoch": 0.9605488850771869,
+      "grad_norm": 1.0410429239273071,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.2407,
+      "step": 35
+    },
+    {
+      "epoch": 0.9879931389365352,
+      "grad_norm": 0.9726614952087402,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.2454,
+      "step": 36
+    },
+    {
+      "epoch": 1.0154373927958833,
+      "grad_norm": 4.215343952178955,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.4031,
+      "step": 37
+    },
+    {
+      "epoch": 1.0428816466552315,
+      "grad_norm": 3.6619632244110107,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.2747,
+      "step": 38
+    },
+    {
+      "epoch": 1.0703259005145798,
+      "grad_norm": 3.1446211338043213,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.2159,
+      "step": 39
+    },
+    {
+      "epoch": 1.097770154373928,
+      "grad_norm": 4.393820762634277,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.2587,
+      "step": 40
+    },
+    {
+      "epoch": 1.1252144082332762,
+      "grad_norm": 1.2491259574890137,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.2152,
+      "step": 41
+    },
+    {
+      "epoch": 1.1526586620926245,
+      "grad_norm": 4.064204692840576,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.2517,
+      "step": 42
+    },
+    {
+      "epoch": 1.1801029159519725,
+      "grad_norm": 1.7868139743804932,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.2029,
+      "step": 43
+    },
+    {
+      "epoch": 1.2075471698113207,
+      "grad_norm": 2.360548734664917,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.2119,
+      "step": 44
+    },
+    {
+      "epoch": 1.234991423670669,
+      "grad_norm": 2.1075613498687744,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.1995,
+      "step": 45
+    },
+    {
+      "epoch": 1.2624356775300172,
+      "grad_norm": 2.620868682861328,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.2165,
+      "step": 46
+    },
+    {
+      "epoch": 1.2898799313893654,
+      "grad_norm": 1.3369566202163696,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.1972,
+      "step": 47
+    },
+    {
+      "epoch": 1.3173241852487134,
+      "grad_norm": 0.9853492379188538,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.2016,
+      "step": 48
+    },
+    {
+      "epoch": 1.3447684391080617,
+      "grad_norm": 1.5131672620773315,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.2154,
+      "step": 49
+    },
+    {
+      "epoch": 1.3722126929674099,
+      "grad_norm": 2.93576717376709,
+      "learning_rate": 0.0,
+      "loss": 0.2323,
+      "step": 50
+    },
+    {
+      "epoch": 1.3722126929674099,
+      "eval_loss": 0.23947130143642426,
+      "eval_runtime": 7.4903,
+      "eval_samples_per_second": 32.843,
+      "eval_steps_per_second": 4.139,
+      "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": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null