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:f0487a7242fcf792d04cf38917995b193c43983567502bcb618620086d8b2cc7
+oid sha256:05d72344ef0d555775244d2fa24ec3348dc3ae724fb51c682c266786b98e4693
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4572da9e950791204cabaead2fb4fe4224b51527fdbf8ae5e4e6892d9091facb
+oid sha256:d76f1f683f06e2fd62e90a86c9f9b6e1b821fb3a0afbedc3f0f6669b11110ebd
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04f3bf1920ef8fe46844df3c26a101fcb5db9b3dba29b5b7df7fcef99e07a225
+oid sha256:2ca07873358125ae0dad45a5c4be3e5eb541976e2dfcf9a1dabb25325dc8d4f6
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5431d11f510fe0c92b7bc427d6d6c86263b1a0127f6140333f31ec73974ed3c1
+oid sha256:99cadee9e3c807116e1f447c8ace67885e97d505fd1b0ba3bfd6d7b54ed877ee
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:928b86ca7104df9f104e9689d470d4921bedb2964b5d0feda037ba2f1b7786f4
+oid sha256:3cf816aba84589e98dab5e2ce40a74524b983a52cb5cfa863778fdb07c78c42a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03fe2ae223c3239e156bd3705fdd076c3ba47e4b07cc2320cf775746cbba638c
+oid sha256:b49b1effe7bd84eb2991c14146839ac4c96bd25cdc2e2496f5fed2e48dff6a2e
 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": 1.293853521347046,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.02096216329525207,
+  "best_metric": 1.2732304334640503,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.04192432659050414,
   "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": 48.985,
       "eval_steps_per_second": 6.127,
       "step": 25
+    },
+    {
+      "epoch": 0.021800649827062153,
+      "grad_norm": 0.1442486196756363,
+      "learning_rate": 5e-05,
+      "loss": 1.2427,
+      "step": 26
+    },
+    {
+      "epoch": 0.022639136358872235,
+      "grad_norm": 0.1324678361415863,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.2241,
+      "step": 27
+    },
+    {
+      "epoch": 0.02347762289068232,
+      "grad_norm": 0.13264364004135132,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.2278,
+      "step": 28
+    },
+    {
+      "epoch": 0.0243161094224924,
+      "grad_norm": 0.132313534617424,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.2359,
+      "step": 29
+    },
+    {
+      "epoch": 0.025154595954302483,
+      "grad_norm": 0.1368257850408554,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.2163,
+      "step": 30
+    },
+    {
+      "epoch": 0.025993082486112568,
+      "grad_norm": 0.14327384531497955,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.2459,
+      "step": 31
+    },
+    {
+      "epoch": 0.02683156901792265,
+      "grad_norm": 0.1744619905948639,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.2904,
+      "step": 32
+    },
+    {
+      "epoch": 0.027670055549732734,
+      "grad_norm": 0.17769135534763336,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.2816,
+      "step": 33
+    },
+    {
+      "epoch": 0.028508542081542815,
+      "grad_norm": 0.22097477316856384,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.2854,
+      "step": 34
+    },
+    {
+      "epoch": 0.029347028613352897,
+      "grad_norm": 0.2638107240200043,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.3145,
+      "step": 35
+    },
+    {
+      "epoch": 0.030185515145162982,
+      "grad_norm": 0.30326229333877563,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.395,
+      "step": 36
+    },
+    {
+      "epoch": 0.031024001676973063,
+      "grad_norm": 0.46151870489120483,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.4473,
+      "step": 37
+    },
+    {
+      "epoch": 0.031862488208783145,
+      "grad_norm": 0.16587065160274506,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.2968,
+      "step": 38
+    },
+    {
+      "epoch": 0.032700974740593226,
+      "grad_norm": 0.14834366738796234,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.1843,
+      "step": 39
+    },
+    {
+      "epoch": 0.033539461272403315,
+      "grad_norm": 0.14233732223510742,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.2286,
+      "step": 40
+    },
+    {
+      "epoch": 0.034377947804213396,
+      "grad_norm": 0.13319115340709686,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.2131,
+      "step": 41
+    },
+    {
+      "epoch": 0.03521643433602348,
+      "grad_norm": 0.13616111874580383,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.2021,
+      "step": 42
+    },
+    {
+      "epoch": 0.03605492086783356,
+      "grad_norm": 0.1343865692615509,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.2018,
+      "step": 43
+    },
+    {
+      "epoch": 0.03689340739964364,
+      "grad_norm": 0.14616534113883972,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.2465,
+      "step": 44
+    },
+    {
+      "epoch": 0.03773189393145373,
+      "grad_norm": 0.16980408132076263,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.2885,
+      "step": 45
+    },
+    {
+      "epoch": 0.03857038046326381,
+      "grad_norm": 0.1766597181558609,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.2422,
+      "step": 46
+    },
+    {
+      "epoch": 0.03940886699507389,
+      "grad_norm": 0.2097931057214737,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.2647,
+      "step": 47
+    },
+    {
+      "epoch": 0.040247353526883974,
+      "grad_norm": 0.2691362202167511,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.2763,
+      "step": 48
+    },
+    {
+      "epoch": 0.041085840058694055,
+      "grad_norm": 0.4423013925552368,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.2612,
+      "step": 49
+    },
+    {
+      "epoch": 0.04192432659050414,
+      "grad_norm": 0.7524447441101074,
+      "learning_rate": 0.0,
+      "loss": 1.5119,
+      "step": 50
+    },
+    {
+      "epoch": 0.04192432659050414,
+      "eval_loss": 1.2732304334640503,
+      "eval_runtime": 164.028,
+      "eval_samples_per_second": 48.986,
+      "eval_steps_per_second": 6.127,
+      "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": 4.16708196040704e+16,
+  "total_flos": 8.33416392081408e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null