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:cb9dd2914c405ed33f42e2858cda918c5114e0d2b8c156b84f15f1c78b333851
+oid sha256:015ca5f1d1e062bb877b26a53c6fa21968d747a6a4ca0bfa66e2affe9125b0fc
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c57a70dc9dd7dbc750e174816d0706409b561a508546ffcc009fdd21200f877
+oid sha256:2c061ceb40cb13c5d5b67385b135918952132a79c389117283d9fb970b3a0b05
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc7b0f7aff2e6d0579e479447429b963621f347d661ed17b566c5e213a4ad064
+oid sha256:ec511fbcd2e0721e60dae91f6e15f21db484ffce8375e253d0669f9b317dd474
 size 14960

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": 0.30522599816322327,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.6861063464837049,
+  "best_metric": 0.2452608197927475,
+  "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": 32.715,
       "eval_steps_per_second": 4.123,
       "step": 25
+    },
+    {
+      "epoch": 0.7135506003430532,
+      "grad_norm": 1.8627270460128784,
+      "learning_rate": 5e-05,
+      "loss": 0.2793,
+      "step": 26
+    },
+    {
+      "epoch": 0.7409948542024014,
+      "grad_norm": 2.5019619464874268,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.2595,
+      "step": 27
+    },
+    {
+      "epoch": 0.7684391080617495,
+      "grad_norm": 3.339423656463623,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.2742,
+      "step": 28
+    },
+    {
+      "epoch": 0.7958833619210978,
+      "grad_norm": 4.57916259765625,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.3306,
+      "step": 29
+    },
+    {
+      "epoch": 0.823327615780446,
+      "grad_norm": 2.4405033588409424,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.2576,
+      "step": 30
+    },
+    {
+      "epoch": 0.8507718696397941,
+      "grad_norm": 2.457447052001953,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.2719,
+      "step": 31
+    },
+    {
+      "epoch": 0.8782161234991424,
+      "grad_norm": 3.9348955154418945,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.2754,
+      "step": 32
+    },
+    {
+      "epoch": 0.9056603773584906,
+      "grad_norm": 3.3448519706726074,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.2563,
+      "step": 33
+    },
+    {
+      "epoch": 0.9331046312178388,
+      "grad_norm": 1.652413010597229,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.2726,
+      "step": 34
+    },
+    {
+      "epoch": 0.9605488850771869,
+      "grad_norm": 0.9518668055534363,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.2411,
+      "step": 35
+    },
+    {
+      "epoch": 0.9879931389365352,
+      "grad_norm": 1.1170496940612793,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.2446,
+      "step": 36
+    },
+    {
+      "epoch": 1.0154373927958833,
+      "grad_norm": 4.179270267486572,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.3761,
+      "step": 37
+    },
+    {
+      "epoch": 1.0428816466552315,
+      "grad_norm": 3.888280153274536,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.248,
+      "step": 38
+    },
+    {
+      "epoch": 1.0703259005145798,
+      "grad_norm": 2.5763416290283203,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.2139,
+      "step": 39
+    },
+    {
+      "epoch": 1.097770154373928,
+      "grad_norm": 4.430254936218262,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.2449,
+      "step": 40
+    },
+    {
+      "epoch": 1.1252144082332762,
+      "grad_norm": 1.2438457012176514,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.205,
+      "step": 41
+    },
+    {
+      "epoch": 1.1526586620926245,
+      "grad_norm": 4.233536720275879,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.2622,
+      "step": 42
+    },
+    {
+      "epoch": 1.1801029159519725,
+      "grad_norm": 3.1736645698547363,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.2163,
+      "step": 43
+    },
+    {
+      "epoch": 1.2075471698113207,
+      "grad_norm": 2.0878634452819824,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.2141,
+      "step": 44
+    },
+    {
+      "epoch": 1.234991423670669,
+      "grad_norm": 1.501262903213501,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.1938,
+      "step": 45
+    },
+    {
+      "epoch": 1.2624356775300172,
+      "grad_norm": 2.856403112411499,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.2086,
+      "step": 46
+    },
+    {
+      "epoch": 1.2898799313893654,
+      "grad_norm": 1.4120512008666992,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.2055,
+      "step": 47
+    },
+    {
+      "epoch": 1.3173241852487134,
+      "grad_norm": 0.8188878893852234,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.2022,
+      "step": 48
+    },
+    {
+      "epoch": 1.3447684391080617,
+      "grad_norm": 1.1168948411941528,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.2211,
+      "step": 49
+    },
+    {
+      "epoch": 1.3722126929674099,
+      "grad_norm": 2.3238978385925293,
+      "learning_rate": 0.0,
+      "loss": 0.2294,
+      "step": 50
+    },
+    {
+      "epoch": 1.3722126929674099,
+      "eval_loss": 0.2452608197927475,
+      "eval_runtime": 7.5089,
+      "eval_samples_per_second": 32.761,
+      "eval_steps_per_second": 4.128,
+      "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