Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:086b4c963ca657b0d9c5f5b3c394ef8e77e69efcafb905c856dd145f398fecba
+oid sha256:d40265e215dded8cfb9f70095babb734c90eb8aab448108e681447ad4cb262a5
 size 432223744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d0af947c632dfb5ebbb96228ee03b67a74cc3ed40ee0e2e797f6bd74a1d439f
+oid sha256:3430eca43c21f190a4e2a26c015ff3839ff8627efb1af29d09e50a9c648158d3
 size 864785974

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b09617bbaa65e74365a54b1914592032cd6c8fef024891a576dd2fef4bd8b2d3
+oid sha256:549c67ff441572ea072e74ed8c550b78ed566b7f028fa17b492219c2b2002bc5
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3579f1de909cf6aaf38d67919cacaf3ed457437bb1decdacecfd206d2d2350a6
+oid sha256:dc52466e9ae50f73d678f54c9b45698e1d3c8285a91095b81520da49520c5b2b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:746867c9fe2c578e782d712eb3ba26db9f8ae2a2fbc055b843b2251bba676cca
+oid sha256:9bac34f83de421818836841fcd3f2500d08ffc64842f39f25cd9084b156df9f1
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11b059657c4086d3f466776b76f4d0dba4a2ee79d04f1e65dd8f122ca658a6f4
+oid sha256:473431b0c08834f9805007bd43789e26cb9f81619fe887ff31ad69269e762b7a
 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": 3.40779447555542,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.028115554930765445,
+  "best_metric": 3.1929125785827637,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.05623110986153089,
   "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": 19.386,
       "eval_steps_per_second": 2.424,
       "step": 25
+    },
+    {
+      "epoch": 0.029240177127996064,
+      "grad_norm": 3.1716904640197754,
+      "learning_rate": 5e-05,
+      "loss": 2.7735,
+      "step": 26
+    },
+    {
+      "epoch": 0.03036479932522668,
+      "grad_norm": 2.3801329135894775,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 2.9328,
+      "step": 27
+    },
+    {
+      "epoch": 0.031489421522457296,
+      "grad_norm": 2.1450247764587402,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 3.0893,
+      "step": 28
+    },
+    {
+      "epoch": 0.032614043719687916,
+      "grad_norm": 1.962648630142212,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 3.247,
+      "step": 29
+    },
+    {
+      "epoch": 0.033738665916918535,
+      "grad_norm": 1.683558702468872,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 3.0529,
+      "step": 30
+    },
+    {
+      "epoch": 0.034863288114149155,
+      "grad_norm": 1.3883835077285767,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 3.2441,
+      "step": 31
+    },
+    {
+      "epoch": 0.035987910311379774,
+      "grad_norm": 1.3524730205535889,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 3.3116,
+      "step": 32
+    },
+    {
+      "epoch": 0.03711253250861039,
+      "grad_norm": 1.480422019958496,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 3.4448,
+      "step": 33
+    },
+    {
+      "epoch": 0.038237154705841006,
+      "grad_norm": 1.6115326881408691,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 3.5494,
+      "step": 34
+    },
+    {
+      "epoch": 0.039361776903071626,
+      "grad_norm": 1.7949885129928589,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 3.6366,
+      "step": 35
+    },
+    {
+      "epoch": 0.040486399100302245,
+      "grad_norm": 1.9349582195281982,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 3.5999,
+      "step": 36
+    },
+    {
+      "epoch": 0.04161102129753286,
+      "grad_norm": 2.4920969009399414,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 3.9289,
+      "step": 37
+    },
+    {
+      "epoch": 0.04273564349476348,
+      "grad_norm": 2.61846661567688,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.923,
+      "step": 38
+    },
+    {
+      "epoch": 0.043860265691994096,
+      "grad_norm": 1.408206582069397,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 2.5878,
+      "step": 39
+    },
+    {
+      "epoch": 0.044984887889224716,
+      "grad_norm": 1.4055184125900269,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 2.8857,
+      "step": 40
+    },
+    {
+      "epoch": 0.04610951008645533,
+      "grad_norm": 1.3500643968582153,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 2.9791,
+      "step": 41
+    },
+    {
+      "epoch": 0.04723413228368595,
+      "grad_norm": 1.2070780992507935,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.9451,
+      "step": 42
+    },
+    {
+      "epoch": 0.04835875448091657,
+      "grad_norm": 1.2396039962768555,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 3.1089,
+      "step": 43
+    },
+    {
+      "epoch": 0.04948337667814719,
+      "grad_norm": 1.230837106704712,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 3.0257,
+      "step": 44
+    },
+    {
+      "epoch": 0.050607998875377806,
+      "grad_norm": 1.293530821800232,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 3.257,
+      "step": 45
+    },
+    {
+      "epoch": 0.05173262107260842,
+      "grad_norm": 1.3561540842056274,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 3.2339,
+      "step": 46
+    },
+    {
+      "epoch": 0.05285724326983904,
+      "grad_norm": 1.4467884302139282,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 3.3938,
+      "step": 47
+    },
+    {
+      "epoch": 0.05398186546706966,
+      "grad_norm": 1.6693027019500732,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 3.4668,
+      "step": 48
+    },
+    {
+      "epoch": 0.05510648766430028,
+      "grad_norm": 1.9177041053771973,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 3.6238,
+      "step": 49
+    },
+    {
+      "epoch": 0.05623110986153089,
+      "grad_norm": 2.617114543914795,
+      "learning_rate": 0.0,
+      "loss": 4.1492,
+      "step": 50
+    },
+    {
+      "epoch": 0.05623110986153089,
+      "eval_loss": 3.1929125785827637,
+      "eval_runtime": 308.9756,
+      "eval_samples_per_second": 19.387,
+      "eval_steps_per_second": 2.424,
+      "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": 3.315690861756416e+17,
+  "total_flos": 6.631381723512832e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null