Training in progress, step 6300

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3febec860772b82c489867736d215315d0909ffc43a3ba7b9fbc1d0b41fd7a20
+oid sha256:7a03009057bc17a55fb03559fceee9416e58df44f2b8cad404853c77ef5e25ff
 size 500897101

{checkpoint-5900 → checkpoint-6200/adapter_model}/adapter_config.json

@@ -14,13 +14,13 @@
   "r": 32,
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj",
-    "gate_proj",
     "up_proj",
-    "o_proj",
+    "gate_proj",
+    "down_proj",
+    "q_proj",
     "k_proj",
-    "down_proj"
+    "o_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

{checkpoint-5900 → checkpoint-6200/adapter_model}/adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3b3da1c54329907c1913ad730b0e8c5d24d4c2d49e4f95aa7976664afc0a98c
+oid sha256:3febec860772b82c489867736d215315d0909ffc43a3ba7b9fbc1d0b41fd7a20
 size 500897101

{checkpoint-5900/adapter_model → checkpoint-6300}/adapter_config.json

@@ -14,13 +14,13 @@
   "r": 32,
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj",
-    "gate_proj",
     "up_proj",
-    "o_proj",
+    "gate_proj",
+    "down_proj",
+    "q_proj",
     "k_proj",
-    "down_proj"
+    "o_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

{checkpoint-5900/adapter_model → checkpoint-6300}/adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3b3da1c54329907c1913ad730b0e8c5d24d4c2d49e4f95aa7976664afc0a98c
+oid sha256:7a03009057bc17a55fb03559fceee9416e58df44f2b8cad404853c77ef5e25ff
 size 500897101

{checkpoint-5900 → checkpoint-6300}/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1197bafa9ae84ea7a453b741f03a67406157df8c322c0f2e87f2e9c99c7e6415
+oid sha256:95b7209d5ad4284033cb4767ae444e7a78eba53804e8f6dfd2ae1d008b403ecb
 size 1001752701

{checkpoint-5900 → checkpoint-6300}/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6b970d7fefc137c6fa7c1f3ec5751405f46258d274a85e6d4372f5c1b430100
+oid sha256:4b0892c501b6dd52efec58730585273a276e5cf9f6937d96e9fa38ae5af9abd6
 size 27772

{checkpoint-5900 → checkpoint-6300}/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7c346a11c7d7489d10f88696f09c70a4abe9b4d22e70d081daf287152ba6758
+oid sha256:ed1c7ad44d4c44043a9a1040ab7a8d9bf8ccb6a798963c6beec8678ba53a99d5
 size 27772

{checkpoint-5900 → checkpoint-6300}/rng_state_10.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28cc2f86fa3f892a60fcd12ec1c513fe4892758b164d8b6dcaf3ffad379de4bf
+oid sha256:51696bdc2a942c4b6659d0c7c032d47971cc912461202edc9cbf84be5b00b9d4
 size 27789

{checkpoint-5900 → checkpoint-6300}/rng_state_11.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7e9eaa5d2c6ecd694c6005f784826c1ef125cd869dc4ae397dc6622d332750e
+oid sha256:cf2dc121d536b338f7f7ab71844d47b47fa50424082757312612a1ffb43ce6d6
 size 27789

{checkpoint-5900 → checkpoint-6300}/rng_state_12.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38acd1e9cddbb15c52d3524a7f3e3b0813e9d4cd4aa950fe53314f0b60178040
+oid sha256:600cbb989fd1bd997e07afb75b51b0e9bb6bba91f6f55fd115d8b32524b2c2a2
 size 27789

{checkpoint-5900 → checkpoint-6300}/rng_state_13.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0c474d8b008c60069849057cd5597c90d8f9e8db24500adaab180041a48449f
+oid sha256:4f2f55cc04908fd235b9c2e1fae05ac4e683f052b4ea8b4e70cb8d917af90168
 size 27789

{checkpoint-5900 → checkpoint-6300}/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b70d819dbeb60759d92edd51269d8cee2700d47a9ed7c6a47d97f93849e55bb0
+oid sha256:daf71be757b88dd90b278fe0d6abf41fdfd54d283da14639c698e92c6ee6204c
 size 27772

{checkpoint-5900 → checkpoint-6300}/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d28ba4337f3d0ed31c728bf8fbbd7c00c8014b3f57ffbf29863e421ce59080c
+oid sha256:d8d3a91b3606a86dfbe9591df14b8680debec4ee7ccd893c21fc87ce694c0de6
 size 27772

{checkpoint-5900 → checkpoint-6300}/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00c43f507f234617c2e9bcf5dd72636cec19310803bce07ad6514e0e90814858
+oid sha256:d6af24a322399a9faa75e21470cca01ffb561d5fc8d90ce309043c8aede63c59
 size 27772

{checkpoint-5900 → checkpoint-6300}/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29979a24bd6bef289a10c8e120d56f27b5f058b309d98caf16f123a7a861dce9
+oid sha256:6e40c161f1898bfa1d6decd05f837beb821a821ae27f1e34a964a8ec433edd39
 size 27772

{checkpoint-5900 → checkpoint-6300}/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78aa8d7c2497285c4d5739872ca5ceac97b5b636a89d97a0185297b5bbd049d6
+oid sha256:d5a9e186bb4ebc2493f0fa088e88be12fd79ba92df4b0d1984d04b88fb44615e
 size 27772

{checkpoint-5900 → checkpoint-6300}/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04a7b8a1abaea1776e2ddd83a1b3d050ed23897ede63223f377eb777702f7a0f
+oid sha256:5389b58d9b2d1b81fdd14d9dfa214e64e33c18b1e015479871952bbf5fbc9a9f
 size 27772

{checkpoint-5900 → checkpoint-6300}/rng_state_8.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acca6763654c1dff02cf8af98fff17739233e457ad75b6ff4297b68efc173984
+oid sha256:964ebee03695528c749c601db479754170f0284c59a3215d8dfcd92e48f3ae00
 size 27772

{checkpoint-5900 → checkpoint-6300}/rng_state_9.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a71a0b91f398dff81646dcd42cd8df3dfca54a277c75bab4cc51332fdf4a4768
+oid sha256:20f2b548b149282f75edcff3a569214186d9d16e83d775ade7543af31b397f99
 size 27772

{checkpoint-5900 → checkpoint-6300}/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f769241bb104f866dbb417f19005672d382c2f1d72ce0cc8284c37b0a8dd3e0e
+oid sha256:fc486d593be71181a7b350459598105a51de879e181677c7b4a0bcff932974dc
 size 627

{checkpoint-5900 → checkpoint-6300}/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.2877084141139976,
-  "global_step": 5900,
+  "epoch": 2.44280728964715,
+  "global_step": 6300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1438,11 +1438,115 @@
       "learning_rate": 2.6618481296414522e-05,
       "loss": 0.7722,
       "step": 5900
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 2.5931770576738313e-05,
+      "loss": 0.7698,
+      "step": 5925
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 2.525271205441837e-05,
+      "loss": 0.7751,
+      "step": 5950
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 2.45813758849028e-05,
+      "loss": 0.766,
+      "step": 5975
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 2.3917831425821824e-05,
+      "loss": 0.7673,
+      "step": 6000
+    },
+    {
+      "epoch": 2.33,
+      "eval_loss": 0.806900680065155,
+      "eval_runtime": 58.3254,
+      "eval_samples_per_second": 12.516,
+      "eval_steps_per_second": 0.909,
+      "step": 6000
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 2.3262147229821984e-05,
+      "loss": 0.7679,
+      "step": 6025
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 2.2614391037483983e-05,
+      "loss": 0.7704,
+      "step": 6050
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 2.1974629770324106e-05,
+      "loss": 0.7661,
+      "step": 6075
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 2.1342929523880416e-05,
+      "loss": 0.7652,
+      "step": 6100
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 2.0719355560884246e-05,
+      "loss": 0.765,
+      "step": 6125
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 2.010397230451766e-05,
+      "loss": 0.7704,
+      "step": 6150
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 1.9496843331757784e-05,
+      "loss": 0.767,
+      "step": 6175
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 1.8898031366808467e-05,
+      "loss": 0.7654,
+      "step": 6200
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 1.830759827462004e-05,
+      "loss": 0.7753,
+      "step": 6225
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 1.7725605054497906e-05,
+      "loss": 0.7725,
+      "step": 6250
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 1.7152111833800522e-05,
+      "loss": 0.7698,
+      "step": 6275
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 1.6587177861727454e-05,
+      "loss": 0.7703,
+      "step": 6300
     }
   ],
   "max_steps": 7737,
   "num_train_epochs": 3,
-  "total_flos": 2.5410887248997515e+19,
+  "total_flos": 2.7132330413479952e+19,
   "trial_name": null,
   "trial_params": null
 }

{checkpoint-5900 → checkpoint-6300}/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df5d13b3f1b9942f80afde79010ef0947feee3df761d245fef1699bc397648b2
+oid sha256:e85009bca9623c846e630c294adb80ecbcd9e720da8da9f9ee5311b562908b91
 size 4027