Training in progress, step 500

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "bigscience/bloom-560m",
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "BloomForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "attention_softmax_in_fp32": true,
+  "bias_dropout_fusion": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "masked_softmax_fusion": true,
+  "model_type": "bloom",
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 24,
+  "offset_alibi": 100,
+  "pad_token_id": 3,
+  "pretraining_tp": 1,
+  "skip_bias_add": true,
+  "skip_bias_add_qkv": false,
+  "slow_but_exact": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.27.4",
+  "unk_token_id": 0,
+  "use_cache": true,
+  "vocab_size": 250880
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4315c60a5e310b12ce9102efc726635f1cd43ed7dfe2f192a2ac91cb9a050cc0
+size 2236957537

runs/Apr11_05-35-05_fb29cda6ca0b/1681191337.5036135/events.out.tfevents.1681191337.fb29cda6ca0b.924.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b7fb8b2f70c476f0ff605c44b93bec6d9e8baff03c09e236012b98e4326a89a
+size 5856

runs/Apr11_05-35-05_fb29cda6ca0b/events.out.tfevents.1681191337.fb29cda6ca0b.924.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5348897018868678a0de853c8a3d13020d8f75c084b22da1521b6036df180a7a
+size 88

runs/Apr11_05-37-49_fb29cda6ca0b/1681191509.2655795/events.out.tfevents.1681191509.fb29cda6ca0b.26540.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47b9184ad67d0eb9f4f187a7151b9054fbcaed0a6cd8b4fb6a921235f90ff544
+size 5856

runs/Apr11_05-37-49_fb29cda6ca0b/events.out.tfevents.1681191509.fb29cda6ca0b.26540.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63502cea24f32bfa2d0f9218c05e372c3794c4fd99ace15ded54af3c34ffb811
+size 4271

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c583c8f7a9957753b62e469798e6aa719efd53ea953da449bc37fc0e23c0cae4
+size 3579